skills/rodrigowbazevedo/skills/my-prs/Gen Agent Trust Hub

my-prs

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes gh api and gh api graphql commands to fetch data from the GitHub platform. These are legitimate operations for the skill's stated purpose of pull request management.
  • [PROMPT_INJECTION]: The skill processes untrusted external data which constitutes an indirect prompt injection surface. Specifically, it fetches pull request titles and branch names that could contain malicious instructions designed to influence the agent's behavior during rendering.
  • Ingestion points: Pull request titles and branch names (headRefName) retrieved via GitHub GraphQL API in Step 2.
  • Boundary markers: None. The data is directly interpolated into the output format described in Step 5.
  • Capability inventory: Access to the gh command-line tool and standard output capabilities.
  • Sanitization: None specified for the external strings before rendering.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:40 AM
Security Audit — agent-trust-hub — my-prs