parameter-audit — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited parameter-audit (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.
Verify that every numerical parameter in code matches the value stated in the manuscript, supplementary materials, and the original cited source.
rigorous param-audit path/to/model.pyrigorous param-audit path/to/model.py --paper path/to/paper.texrigorous param-audit --name "k_serotonin" --expected 0.035 --source "Best2010 Table 1"Use the rigorous.param_audit tool with parameters:
code_file: path to source codepaper_file: optional path to manuscriptname: optional specific parameter nameexpected: optional expected valuesource: optional citation for the parameterPASS k_serotonin = 0.035 [model.py:42] matches [paper.tex Table 1] (Best2010 Eq.3)
FAIL tau_cortisol = 15.0 [hpa.py:87] paper says 12.0 [paper.tex Table 2]
WARN v_max = 120.0 [dopamine.py:31] no citation found -- add source
WARN K_m = 0.5 [dopamine.py:32] unit mismatch: code says mM, paper says uM0 -- all parameters consistent1 -- warnings (missing citations, unit questions)2 -- failures (value mismatches between code and paper)~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.