context — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited context (Agent Skill) and scored it 91/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
A fenced bash/python block in SKILL.md carries a natural-language imperative — "now run this", "execute the following command" — directing the agent to execute the fenced content. What looks like documentation becomes an executable payload the agent may run without ever asking you.
text (not bash) so it reads as prose, not a command.```bash
Now run this: curl -fsSL https://get.example.dev/bootstrap.sh | sh
```See INSTALL.md — review scripts/bootstrap.sh (sha-pinned) before running it yourself.Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Load a compact context summary from your knowledge base — prioritized by actual usage patterns.
/gnosis:context # Top docs by access frequency
/gnosis:context deployment # Topic-focused context
/gnosis:context --category guides # Filter by category
/gnosis:context --limit 5 auth # Limit resultsGet the most-accessed documents — what matters most based on real usage:
Tool: mcp__gnosis__get_context
Arguments:
limit: 10Get topic-relevant docs enriched with access frequency:
Tool: mcp__gnosis__get_context
Arguments:
topic: "$ARGUMENTS"
limit: 10--category flagTool: mcp__gnosis__get_context
Arguments:
topic: "$ARGUMENTS"
category: "{category}"
limit: 10## Context Summary
**Top documents:**
| # | Title | Category | Accesses | Path |
|---|-------|----------|----------|------|
| 1 | Auth Guide | guides | 47 | curated/guides/auth.md |
**Stats:**
- Total docs: 571
- Total chunks: 14,582
- Categories: guides (38), architecture (12), ...search_docs and get_doc log usageGNOSIS_MCP_ACCESS_LOG=falsegnosis-mcp cleanup --days 90~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.