claim-evidence-map — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited claim-evidence-map (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.
Trace every claim in a manuscript to the specific evidence (data, figure, equation, citation) that supports it. Identify unsupported claims.
rigorous claim-map path/to/paper.texrigorous claim-map path/to/paper.tex --code path/to/src/rigorous claim-map path/to/paper.tex --output claims.jsonUse the rigorous.claim_map tool with parameters:
file: path to manuscriptcode_dir: optional path to source codeoutput: optional output file for structured reportCLAIM 1 "The coupled system exhibits a 28-day oscillation"
Evidence: Figure 2a (direct), Equation 12 (analytical), Table 1 row 5
Strength: STRONG
CLAIM 2 "Serotonin-cortisol coupling produces emergent mood cycling"
Evidence: Figure 4 (direct), ablation in Section 4.2
Strength: STRONG
CLAIM 3 "This framework generalizes to other affective disorders"
Evidence: None found in manuscript
Strength: UNSUPPORTED
-> Action required: add evidence, weaken claim, or remove
CLAIM 4 "Parameters are biologically realistic"
Evidence: Table 1 citations (indirect -- cites source papers)
Strength: MODERATE
-> Suggestion: add direct comparison to clinical measurement ranges0 -- all claims have supporting evidence1 -- some claims have weak or indirect evidence only2 -- unsupported claims found~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.