code-review
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute "repository-supported verification commands" such as tests or linters found within the target repository to verify code correctness.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data in the form of source code, git diffs, and commit history, which serves as a potential surface for indirect prompt injection.
- Ingestion points: Source code files, git diffs, and task-related evidence (SKILL.md).
- Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted code from the agent's instructions.
- Capability inventory: The agent can modify task-tracking documents and execute shell commands for code verification (SKILL.md).
- Sanitization: There is no instruction to sanitize or escape the content of the files being reviewed.
Audit Metadata