pr-workflow
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local commands using
gitand the GitHub CLI (gh) to perform operations such as identifying staged changes, creating feature branches, and submitting pull requests. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it retrieves and summarizes untrusted content from the repository's git diffs.
- Ingestion points: Repository content and commit history are accessed via
git diff --cached --name-onlyandgit diff <base-branch>...HEAD. - Boundary markers: The skill lacks explicit delimiters or instructions to ignore commands embedded within the analyzed code or commit messages.
- Capability inventory: The agent has the ability to execute shell commands (
git,gh) and perform external lookups via themcp__tavily__tavily_searchtool. - Sanitization: No sanitization, escaping, or validation of the repository content is performed before it is processed by the model for summarization.
Audit Metadata