code-review — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited code-review (Agent Skill) and scored it 91/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 1 high-severity and 0 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} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.
ignore/disregard/forget … previous instructions sentence.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.
A structured, language-agnostic code review process that identifies bugs, security issues, performance problems, and style violations. Always produces actionable output with severity ratings.
Read the entire code block before writing any feedback. Understanding the full context prevents false positives and surface-level comments.
Note the language, framework, and apparent purpose. Calibrate expectations accordingly (e.g., prototype vs. production, CLI script vs. library).
Scan specifically for:
pickle.loads, eval, exec on user inputUse this format for each finding:
[SEVERITY] Category: Title
File: path/to/file.py, Line: N
Issue: One sentence describing the problem.
Impact: What could go wrong.
Fix:
<corrected code snippet>Severity levels:
End with:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.