review-changes
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the local environment which could contain malicious instructions.
- Ingestion points: The skill reads git diff outputs, commit logs, and documentation files such as
AGENTS.mdandCLAUDE.md(SKILL.md, Workflow section). - Boundary markers: No specific delimiters or safety warnings are provided to help the agent distinguish between code/data and embedded instructions.
- Capability inventory: The skill utilizes shell commands (
git status,git diff,git log,git show) to retrieve data for analysis (SKILL.md, Inspect The Change Set section). - Sanitization: There is no evidence of sanitization or filtering of the content read from files or git outputs before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute specific shell commands to inspect the state of the repository.
- Evidence: Instructions include the use of
git status --short,git diff --stat, andgit show <commit>to gather context for the code review (SKILL.md, Inspect The Change Set section). These are standard development tools and the usage is scoped to the local repository.
Audit Metadata