wiki-changelog
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- Command Execution: The skill instructs the agent to execute local git commands (e.g.,
git log,git show,git remote) to retrieve repository data. These are standard operations for the skill's stated purpose and operate within the local repository context. - Indirect Prompt Injection Surface: As the skill processes git commit history, it is theoretically susceptible to indirect prompt injection if a malicious actor includes instructions within commit messages. However, the instructions focus on extracting and categorizing data rather than executing content from the logs, which minimizes the risk.
- Repository Resolution: The skill includes a 'MUST DO FIRST' step to determine the repository source, which is a best practice for providing accurate citations and ensuring the agent understands the data source before processing.
Audit Metadata