describing-PRs
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses several shell commands (
git,mkdir) and a custom Python script to interact with the local repository. The scriptfind-merge-base.pyusessubprocess.runto execute git commands. These operations are restricted to the local git environment and are necessary for the skill's primary function of analyzing code changes. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. It ingests untrusted data from the repository's commit logs and file differences (
git log,git diff) and incorporates this data directly into the LLM's context to generate the PR description. - Ingestion points: Commit messages and file diffs gathered in step 2 of
SKILL.md. - Boundary markers: None are explicitly used when interpolating the git output into the generation prompt.
- Capability inventory: The skill has the capability to write files to the
.git/magit/posts/directory and execute local git commands via thefind-merge-base.pyscript. - Sanitization: No sanitization or filtering of the commit messages or diff content is performed before processing.
Audit Metadata