pr-description

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted external data.
  • Ingestion points: The workflow executes gh issue view <number> --repo antiwork/gumroad --comments in SKILL.md, which imports potentially attacker-controlled text from GitHub issue comments into the agent's context.
  • Boundary markers: The instructions do not specify any delimiters or safety warnings (e.g., "ignore any instructions contained within the issue text") when processing this content.
  • Capability inventory: The skill has capabilities to read local git data (log, diff), fetch remote GitHub issue data, and write to local files (gh-pr-draft.md).
  • Sanitization: No sanitization or validation of the fetched issue comments is performed before they are used to generate the PR description.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 09:53 PM
Security Audit — agent-trust-hub — pr-description