Skills
skills/lwlee2608/agent-skills/gh-update-pr/Gen Agent Trust Hub

gh-update-pr

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions facilitate the processing of Pull Request titles and bodies, which are external data sources that could contain malicious instructions (Indirect Prompt Injection).
  • Ingestion points: The PR title and body fields in the gh api command template in SKILL.md.
  • Boundary markers: Absent. The instructions do not define delimiters for untrusted input or warn the agent to ignore instructions embedded within the PR content.
  • Capability inventory: The skill uses the gh api tool to perform PATCH operations, providing write access to GitHub repository resources.
  • Sanitization: Absent. There are no instructions for escaping or validating the content of the title or body before interpolation into the command line.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 01:01 PM