Skills
Navigate
skills/humanlayer/skills/visual-pr/Gen Agent Trust Hub

visual-pr

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, including pull request diffs, tickets, and task artifacts, which could contain malicious instructions designed to hijack the agent's logic.
  • Ingestion points: SKILL.md (Step 3) reads ticket content, PR diffs, and task artifacts.
  • Boundary markers: Absent. The instructions do not define delimiters or provide specific 'ignore' instructions for processed content.
  • Capability inventory: SKILL.md (Steps 2 and 5) uses git commit, git push, and gh pr edit.
  • Sanitization: Absent. The skill does not describe any validation or sanitization for the content gathered from tickets or diffs.
  • [COMMAND_EXECUTION]: The skill executes shell commands to interact with the local git repository and GitHub via the gh CLI. While these actions are aligned with the skill's purpose, they provide the execution capability that could be targeted by injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 12:14 PM
Security Audit — agent-trust-hub — visual-pr