github-actions-trigger

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill facilitates automation by communicating with the official GitHub API at api.github.com, which is a well-known and trusted service for development workflows.- [SAFE]: Authentication is handled using user-provided tokens stored in the agent's context memory, which is a secure and standard practice for avoiding hardcoded credentials.- [EXTERNAL_DOWNLOADS]: The skill fetches workflow runs and log data from GitHub. This is a functional requirement for its monitoring capabilities and targets a trusted service.- [PROMPT_INJECTION]: An attack surface for indirect prompt injection exists because the skill reads external data from GitHub logs (get_logs in SKILL.md) and reports it back to the agent without using specific boundary markers or sanitization. This risk is inherent to tools that monitor external process outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 12:54 AM
Security Audit — agent-trust-hub — github-actions-trigger