github-automation

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from external GitHub repositories, creating a surface for instructions embedded in that data to influence agent behavior.
  • Ingestion points: The agent reads external content from AGENTS.md, contribution documentation, issue comments, labels, pull request bodies, and workflow logs.
  • Boundary markers: None. The skill does not provide specific delimiters or instructions to treat ingested GitHub content as data only, nor does it tell the agent to ignore instructions embedded within those fields.
  • Capability inventory: The skill has broad capabilities including creating/closing issues, merging pull requests, updating branches, dispatching Actions workflows, and modifying repository collaborators and permissions.
  • Sanitization: None. There are no instructions to sanitize, escape, or validate the content of GitHub comments or PR descriptions before they are processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 11:09 PM
Security Audit — agent-trust-hub — github-automation