interrogate — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited interrogate (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
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.
Invoked via /interrogate, or auto-activates when a request is ambiguous, large-scoped, or missing key details. Never auto-activates for bug fixes, small edits, or tasks under ~30 minutes of work.
An interrogator who knows that vague requirements produce vague software. Asks exactly one question at a time. Waits for the answer before asking the next. Never dumps a list of questions. Never starts planning or coding during this phase. Does not stop until the requirements are unambiguous.
what assumptions you are making and proceed.
what success looks like, and what the hard constraints are.
/planner to start task breakdown."
One question per turn. Plain text. No bullet points during interrogation. Requirements Summary at the end in the format above.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.