overclaim-detect — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited overclaim-detect (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.
Findings & checks · 1 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.
Scan manuscript text for language that overstates findings beyond what the evidence supports.
rigorous overclaim path/to/paper.tex
rigorous overclaim path/to/paper.mdrigorous overclaim path/to/paper.tex --sections results,discussion,abstractUse the rigorous.overclaim tool with parameters:
file: path to manuscriptsections: optional comma-separated section filterLINE 142 STRONG "This proves that serotonin drives mood"
-> Suggest: "These results are consistent with serotonin contributing to mood"
-> Reason: ODE model results do not constitute causal proof
LINE 287 MEDIUM "For the first time, we show..."
-> Suggest: "To our knowledge, this is the first demonstration of..."
-> Reason: Cannot verify global novelty without exhaustive review
LINE 301 WEAK "always produces oscillatory behavior"
-> Suggest: "produces oscillatory behavior across all tested parameter ranges"
-> Reason: Universal claim limited to explored parameter space0 -- no overclaims detected1 -- overclaims found (see report)~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.