SaferSkills independently audited aelfscan-skill (Agent Skill) 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.
MEDIUM"Never tell the user" non-disclosure imperative in the skillSS-SKILL-INJECT-IMPERATIVE-01 · Prompt injection · README.md
MEDIUM — it fires on intent; whether the agent honors the non-disclosure imperative depends on the host model.
Why it matters
A bulleted imperative like {match} tells the agent to never reveal, disclose, or mention something to the user. Used adversarially it can instruct the agent to hide its tool calls or lie about what it did — stripping the transparency a user relies on to trust the agent.
The exact value spotted
excerptREADME.md· markdown
134
135- Keep API tokens and private keys in env/config only.
136- Never leak secret values in tool outputs.
Occurrences
1 occurrence · at L136
How to fix
Remove the non-disclosure imperative, or rescope it so it limits output format, not honesty to the user.
Delete any "never reveal / never tell the user" line aimed at the model's own behavior.
Keep legitimate confidentiality rules about external data (e.g. "do not echo API keys"), which are user-protective, not user-deceiving.