generate-pr-description
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill workflow directs the agent to execute multiple git commands locally (such as rev-parse, show-branch, merge-base, diff, and log). It also executes two Node.js scripts provided within the skill directory: tasks-system.mjs for configuration handling and copy-to-clipboard.mjs for system clipboard access.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes git commit messages and diff content which are external, untrusted data sources. (1) Ingestion points: The skill reads output from git log and git diff commands. (2) Boundary markers: No delimiters or specific instructions to ignore embedded commands are used for the git data. (3) Capability inventory: The skill can execute git commands, run local Node.js scripts, and access the system clipboard. (4) Sanitization: No specific sanitization or validation of commit messages is performed before they are used to generate the PR description.
Audit Metadata