skills/canhassancode/skills/pr/Gen Agent Trust Hub

pr

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard development tools including git status, git log, git diff, git push, and the GitHub CLI gh pr create. These are expected tools for a pull request automation skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads external data that could be controlled by an attacker (commit messages and code diffs).
  • Ingestion points: git log and git diff output are ingested into the agent's context to generate the PR summary.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore instructions embedded within the git logs or diffs.
  • Capability inventory: The agent has the capability to push code (git push) and create pull requests (gh pr create).
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the git history.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 08:13 AM