generate-changelog
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs shell command execution to interact with local git repositories, including
git pull --ff-onlyto update repositories andgit log,git show, andgit diffto extract change history. - [INDIRECT_PROMPT_INJECTION]: The skill processes content from git history and pull request descriptions which can contain instructions intended to influence the agent's behavior.
- Ingestion points: The skill ingests untrusted data from
git log,git show, andgit diffoutputs, as well as PR descriptions from local repositories (SKILL.md, Step 3). - Boundary markers: There are no boundary markers or explicit instructions provided to the subagents to distinguish between the commit data being analyzed and instructions to the agent.
- Capability inventory: The skill can execute git commands and write markdown files to the local file system (SKILL.md, Steps 2, 3, and 5).
- Sanitization: There is no evidence of sanitization, validation, or escaping of the ingested text before it is passed to the subagents for analysis.
Audit Metadata