github-pull-request

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill possesses a vulnerability surface for indirect prompt injection as it processes data from the local repository.
  • Ingestion points: The skill reads file contents, diffs, and commit history from the target repository using git commands.
  • Boundary markers: Absent. The skill does not use delimiters or explicit instructions to the AI to ignore instructions embedded in the analyzed code.
  • Capability inventory: The skill has the capability to write to GitHub (creating PRs) and output content to the chat interface.
  • Sanitization: Absent. There is no evidence of escaping or validation of the data pulled from the repository before it is used to generate PR titles and descriptions.
  • [Command Execution] (SAFE): The skill executes standard, read-only git commands (git diff, git log, git status) to gather context. No arbitrary command execution or shell injection patterns were detected.
  • [Prompt Injection] (SAFE): While the skill enforces a specific 'chill dude' persona and an English-only requirement, these are behavioral constraints and do not attempt to bypass core AI safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:30 PM