mcp-llms-full— rules

mcp-llms-full — independently scanned and version-tracked by SaferSkills.

Is mcp-llms-full safe to install?

SaferSkills independently audited mcp-llms-full (Rules) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
96/100
●●●●●●●●●●
Re-scan~30s
Latest scan
ScannedJun 23, 2026 · 133d ago
Scans run0 over 90 days
Detectors55 checks · 5 categories
Findings1 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
88
30.8 pts
Supply chainhash, typosquat, maintainer, lockfile
20%
100
20.0 pts
Maintenancestaleness, pinning, CI
15%
100
15.0 pts
TransparencySKILL.md, perms, README
15%
100
15.0 pts
Communityinstalls, verify, response
15%
100
15.0 pts

Findings & checks · 1 flagged

Securityscore 88 · 1 finding
MEDIUMRules file commands the agent to hide or withhold informationSS-RULES-INJECT-IMPERATIVE-01 · Prompt injection · .cursor/rules/mcp-llms-full.mdc
MEDIUM — the instruction reshapes the agent's disclosure behaviour silently across every session, not one prompt.
Why it matters

A rules file is loaded verbatim into the agent as standing instructions for every session. A non-disclosure imperative like * Don't leak sensitive information steers the agent to conceal behaviour, hide tool calls, or withhold information on every prompt — never appearing in any single conversation you'd review.

The exact value spotted
excerpt.cursor/rules/mcp-llms-full.mdc· markdown
731 
7324. **Error handling**
733* Don't leak sensitive information
734* Log security-relevant errors
735* Implement proper cleanup
Occurrences
1 occurrence · at L733
How to fix
Remove the non-disclosure imperative, or restate it as a neutral confidentiality guideline scoped to data, not the agent's honesty.
  1. Delete or reword the highlighted instruction so it describes a data-handling boundary (e.g. "keep secrets out of logs") rather than commanding the agent to hide its actions.
  2. Confirm no remaining rule tells the agent to lie about, conceal, or refuse to disclose its own behaviour.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-RULES-INJECT-IMPERATIVE-01sha2569689dd12f118adcc…rubric 365aacaView on GitHub
Supply chainscore 100 · 0 findings
✓—All supply chain checks passedNo findings in this category for the latest scan.pass
Maintenancescore 100 · 0 findings
✓—All maintenance checks passedNo findings in this category for the latest scan.pass
Transparencyscore 100 · 0 findings
✓—All transparency checks passedNo findings in this category for the latest scan.pass
Communityscore 100 · 0 findings
✓—All community checks passedNo findings in this category for the latest scan.pass
Vendor response · right of reply
Are you the maintainer? Submit a response →

Audit the pieces. Scan the whole. Decide.

~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.