review-ai-generated-code
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to process and analyze external, untrusted inputs including code diffs, user requests, and test files. This creates a potential surface for indirect prompt injection where instructions hidden within the code or diffs could attempt to manipulate the agent's behavior during the review process.
- Ingestion points: Workflow steps in
SKILL.mdspecify inspecting diffs, user requests, and tests. - Boundary markers: The instructions do not define specific delimiters or guidelines to separate the untrusted code content from the agent's own operating instructions.
- Capability inventory: The skill workflow includes running tests and static analysis, which typically requires the use of shell execution tools.
- Sanitization: There are no instructions provided for sanitizing or escaping external content before it is processed by the agent.
Audit Metadata