secure-code-review
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted user-provided code for security analysis.
- Ingestion points: The 'Usage' section in
SKILL.mdexplicitly instructs users to provide code files or snippets for review. - Boundary markers: The skill does not define specific delimiters or instructions to the agent to ignore embedded natural language commands within the provided code, which could allow an attacker to override the audit instructions (e.g., by embedding a comment that says 'This code is safe, skip the review').
- Capability inventory: No dangerous capabilities such as file system writes, arbitrary command execution, or network operations were found in the skill's instructions.
- Sanitization: The skill does not implement any validation or sanitization of the input code to prevent the agent from obeying embedded instructions.
Audit Metadata