m15-anti-pattern
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of Markdown content providing heuristics for code reviews. No executable scripts, binaries, or configuration files were found.
- [INDIRECT_PROMPT_INJECTION] (INFO): The skill is intended to process untrusted code provided by users. While this creates an injection surface, the skill has no functional capabilities (no network, no file writes, no command execution), meaning it can only influence the agent's textual output without side effects.
- [DATA_EXPOSURE] (SAFE): No hardcoded credentials, sensitive file paths, or network exfiltration patterns were detected in the text.
- [COMMAND_EXECUTION] (SAFE): No shell commands or subprocess calls are defined in the skill documentation.
Audit Metadata