code-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: As the skill is intended to process external code for review, it has a surface for indirect prompt injection where malicious instructions could be embedded in the code being analyzed.\n
- Ingestion points: The skill ingests code, pull request data, and configuration files (SKILL.md).\n
- Boundary markers: No specific delimiters or instructions to ignore embedded content are defined in the instructions.\n
- Capability inventory: The skill file contains no executable code, tool calls, or network request patterns.\n
- Sanitization: No sanitization or input validation logic is present in the markdown instructions.\n- [SAFE]: The skill is purely instructional and lacks any components that could execute commands, exfiltrate data, or persist on a system. All analyzed content is descriptive and consistent with its stated purpose.
Audit Metadata