skills/lgtm-hq/ai-skills/issue/Gen Agent Trust Hub

issue

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read existing issues and ingest user requirements to generate new issue content, creating a vulnerability to malicious instructions embedded in external data.
  • Ingestion points: The agent reads data from the repository using gh issue list and accepts input from users to 'Gather requirements'.
  • Boundary markers: The skill uses Markdown templates to structure output, but lacks explicit instructions to the agent to ignore or sanitize potential instructions found within existing issue descriptions or comments.
  • Capability inventory: The skill utilizes gh issue list, gh issue create, and gh issue comment to interact with the GitHub API.
  • Sanitization: No specific sanitization or validation steps are defined for processing the data retrieved from external GitHub issues before it is incorporated into new prompts or comments.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 09:26 AM
Security Audit — agent-trust-hub — issue