go-review
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the local git repository and manage report files.
- Evidence: Executes git diff HEAD, git diff --cached, and mkdir -p in SKILL.md.
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to instructions embedded in the source code it analyzes, which could attempt to manipulate the review outcome.
- Ingestion points: Untrusted code changes are ingested via git diff output in SKILL.md.
- Boundary markers: There are no explicit markers or instructions to the model to ignore natural language instructions found within the code hunks.
- Capability inventory: The skill has the ability to execute shell commands (git, mkdir) and write files to the local /tmp directory.
- Sanitization: The skill does not perform sanitization or filtering on the diff content before it is processed by the agent.
Audit Metadata