pr-draft-summary
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard git commands (
git rev-parse,git status,git diff,git log) to gather information about the current working directory and commit history. These operations are essential for the skill's purpose and are performed within the local repository context. - [PROMPT_INJECTION]: The skill handles data from git logs and diffs, which could contain untrusted input from commit messages or code changes. This identifies a surface for indirect prompt injection; however, because the skill only outputs descriptive text and does not have write access or network capabilities, the risk is negligible. Ingestion points: SKILL.md (collecting command outputs). Boundary markers: Absent; untrusted git content is not isolated from instructions. Capability inventory: The skill is restricted to text generation and lacks file-writing or network-exfiltration capabilities. Sanitization: No explicit sanitization of git metadata is performed.
Audit Metadata