rules-lawyer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of natural language instructions and does not reference or execute any scripts, binaries, or shell commands.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data in the form of rulebook passages pasted by users. While this creates an injection surface, the risk is negligible as the skill has no tools or system capabilities to exploit.\n
- Ingestion points: User-supplied rulebook text and situation descriptions (SKILL.md).\n
- Boundary markers: No specific delimiters are used to wrap external text.\n
- Capability inventory: Zero tools, network operations, or file system access points are defined.\n
- Sanitization: No filtering or sanitization of external text is performed.\n- [SAFE]: No malicious patterns such as obfuscation, hardcoded credentials, or persistence mechanisms were detected.
Audit Metadata