wiki-changelog
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: Executes standard local git commands including
git remote get-url originandgit log. These operations are essential for the skill's primary function of analyzing repository history. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from commit messages.
- Ingestion points: Processes output from
git logwhich consists of strings provided by any user with commit access to the repository. - Boundary markers: The prompt lacks explicit delimiters or instructions to the agent to disregard instructions found within commit messages.
- Capability inventory: The skill uses subprocess calls for git operations and formats external data for agent output.
- Sanitization: No validation or filtering is applied to the commit history before it is passed to the LLM for summarization.
Audit Metadata