adversarial-review — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited adversarial-review (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.
Simulate a rigorous, skeptical peer review to identify weaknesses, gaps, and vulnerabilities in a manuscript before submission.
rigorous review path/to/paper.texrigorous review path/to/paper.tex --focus methodology
rigorous review path/to/paper.tex --focus novelty
rigorous review path/to/paper.tex --focus reproducibilityrigorous review path/to/paper.tex --persona "computational neuroscience"
rigorous review path/to/paper.tex --persona "statistics"Use the rigorous.review tool with parameters:
file: path to manuscriptfocus: optional aspect to focus onpersona: optional reviewer domain expertiseFATAL No ablation study separating coupling contribution from subsystem behavior.
A reviewer will ask: "How do you know this isn't just the HPA model alone?"
MAJOR Section 3: Claims emergent behavior but does not define emergence formally.
Suggest: Add definition and cite Thompson & Varela 2001.
MAJOR Figure 4: No error bars or confidence bands on simulation trajectories.
Suggest: Run ensemble with parameter perturbation, show spread.
MINOR Abstract line 3: "novel framework" -- reviewers are skeptical of self-assessed
novelty. Suggest: let the contribution speak for itself.
MINOR References: 8 of 32 citations are self-citations (25%). May raise concerns.0 -- no fatal or major issues found1 -- major issues found2 -- fatal issues found~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.