skills/okisdev/ai-reference/verify-pr/Gen Agent Trust Hub

verify-pr

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell command execution to gather repository context and fetch PR data.
  • Dynamic Context Injection: The skill executes gh repo view, git symbolic-ref, and git branch at load time to populate metadata.
  • Runtime Execution: The skill instructs the agent to use gh pr view, gh pr diff, and gh issue view to retrieve external content for analysis.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing untrusted external content.
  • Ingestion points: External data enters the agent context via PR titles, bodies, comments, and linked GitHub issue descriptions (SKILL.md, Process steps 1 & 2).
  • Boundary markers: Absent. The instructions do not specify any delimiters or safety warnings to treat the fetched content as untrusted.
  • Capability inventory: The agent has the ability to execute shell commands (gh, git), read files, and grep through the codebase (SKILL.md, Process step 4).
  • Sanitization: Absent. No validation or filtering of the fetched PR/issue content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 02:32 AM
Security Audit — agent-trust-hub — verify-pr