Code Review
Pass
Audited by Gen Agent Trust Hub on Jun 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it is designed to analyze untrusted source code without using boundary markers. An attacker could place malicious instructions inside the code being reviewed to alter the agent's behavior.
- Ingestion points: Untrusted source code files ingested via triggers like 'review' and 'audit'.
- Boundary markers: Absent; there are no instructions to use delimiters or XML tags to separate the code content from the review instructions.
- Capability inventory: The skill is designed to interact with the 'RuleCatch' MCP server, which could be an target for manipulation if an injection is successful.
- Sanitization: No sanitization or content filtering is specified for the code before it is processed by the agent.
Audit Metadata