io.github.stackscribe-ai/coding-agent-audit
PYPI · CODING-AGENT-AUDIT
Audits Claude Code/Cursor MCP configs for supply-chain backdoors and risky permissions.
Available components
Last scanned (18 hours ago)
Scores higher than 64% of PyPI servers
Category Security
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
- 1 of 28 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 0 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability65
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 815 tokens (~163/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management13
- Stability observed for 4 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 0% of tool parameters carry a description.Fail
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 6 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 3 Nov 26 0
- Malware scan: unverified → pass ▲ security
- Schema quality: 145 → 163 ▼ functional
- Schema quality: 436 → 598 ▼ functional
- Package version: 0.6.0 → 0.11.0 functional
- Package version: 0.6.0 → 0.10.0 functional
- Package version: 0.6.0 → 0.9.0 functional
- Package version: 0.6.0 → 0.8.0 functional
- Package version: 0.6.0 → 0.7.0 functional
- Package version: 0.6.0 → 0.6.1 functional
- 2 Nov 26 −14
- Malware scan: pass → unverified ▼ security
- Schema quality: pass → fail ▼ functional
- Stability: unverified → 0.07 ▲ functional
- Package version: 0.3.2 → 0.6.0 functional
- 1 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 31 Oct 26 52
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Analysed pypi/coding-agent-audit@0.11.0
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | pypi |
| Reason | No attestation published |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| build_backend | allowlisted | setuptools.build_meta |
Background: Why install scripts are a supply-chain risk →
Dependencies 28 packages
| Packages resolved | 28 |
|---|---|
| No linked repository | 1 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
scan_for_known_backdoors ~71
Scan this machine for known, publicly-documented indicators of compromise from AI-coding-assistant supply-chain attacks (SSH backdoor keys, C2 processes, persistence via cron/LaunchAgent/scheduled task, the trojanized extension.js hash). Read-only; no file is modified.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
scan_mcp_config ~118
Scan this machine's Claude Code / Claude Desktop / MCP config files for risky patterns: hooks that pipe a remote download into a shell, overly broad auto-approved permission rules (e.g. 'Bash(*)'), unpinned MCP server packages, raw IP literals in hook commands or env vars. Args: project_dir: optional path to a project whose .claude/ and .mcp.json should also be scanned, in addition to the user's home-directory config.
| Name | Type | Req | Description |
|---|---|---|---|
| project_dir | – | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
scan_mcp_phantom_packages ~217
Check the `npx`/`uvx`/`pipx run` commands in this machine's (and optionally a project's) MCP server config against the npm/PyPI registries, and flag any package name that doesn't actually exist there - the "MCPhantom" pattern (Glow Labs, Nov 2026): a coding agent fills in a plausible-sounding MCP server name from training data, or copies one from a long-archived tutorial whose package was since renamed or unpublished. An attacker can register that exact name and have it run as the MCP server, with the user's own permissions, the next time the config is loaded. Read-only HTTP lookups only; this never connects to or executes the MCP server itself. Args: project_dir: optional path to a project whose .claude/ and .mcp.json should also be scanned, in addition to the user's home-directory config.
| Name | Type | Req | Description |
|---|---|---|---|
| project_dir | – | – | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
scan_phantom_dependencies ~139
Check a project's package.json / requirements.txt / pyproject.toml dependencies against the npm/PyPI registries and flag any package name that doesn't actually exist there. AI coding assistants occasionally hallucinate a plausible-but-nonexistent package name; if one ends up in a manifest, an attacker can register that exact name with malicious code and have it silently installed on the next install ("slopsquatting"). Read-only HTTP lookups only; nothing is installed. Args: project_dir: path to the project directory containing the manifest file(s) to check.
| Name | Type | Req | Description |
|---|---|---|---|
| project_dir | string | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
scan_tool_descriptions ~162
Scan a list of MCP tool definitions (the 'tools/list' response an MCP server returns, e.g. [{"name": "search", "description": "..."}]) for instructions hidden in the description field - 'tool definition injection'. A malicious or compromised MCP server can register a tool whose description tells the LLM to also call a second, attacker-controlled tool, or to hide an action from the user, without ever shipping malicious code in a package. Pass another MCP server's own tools/list output straight through; this never connects to or executes any server itself. Args: tools: list of tool definitions, each with at least a "description" field.
| Name | Type | Req | Description |
|---|---|---|---|
| tools | array | yes | – |
| Name | Type | Req | Description |
|---|---|---|---|
| result | string | yes | – |
No examples provided.
How do I install the io.github.stackscribe-ai/coding-agent-audit MCP server?
io.github.stackscribe-ai/coding-agent-audit runs locally as a PyPI package, launched with uvx coding-agent-audit. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
pypi · coding-agent-audit
claude mcp add stackscribe-ai-coding-agent-audit -- uvx coding-agent-audit
What is the io.github.stackscribe-ai/coding-agent-audit MCP server?
io.github.stackscribe-ai/coding-agent-audit is an MCP server listed in the public MCP registry as io.github.stackscribe-ai/coding-agent-audit. Audits Claude Code/Cursor MCP configs for supply-chain backdoors and risky permissions. This page covers its PyPI package (coding-agent-audit).
Is the io.github.stackscribe-ai/coding-agent-audit MCP server safe to use?
io.github.stackscribe-ai/coding-agent-audit scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.stackscribe-ai/coding-agent-audit MCP server expose?
io.github.stackscribe-ai/coding-agent-audit exposes 5 tools: scan_for_known_backdoors, scan_mcp_config, scan_phantom_dependencies, scan_mcp_phantom_packages, scan_tool_descriptions. Their descriptions and schemas cost roughly 707 tokens of context every time the server is loaded.
Is the io.github.stackscribe-ai/coding-agent-audit MCP server still maintained?
io.github.stackscribe-ai/coding-agent-audit is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.stackscribe-ai/coding-agent-audit MCP server under?
io.github.stackscribe-ai/coding-agent-audit declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.