actions-manager

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill utilizes official GitHub documentation and the standard GitHub CLI tool, which are established and trustworthy resources.
  • [NO_CODE]: The skill contains no executable scripts, binaries, or references to external code packages.
  • [PROMPT_INJECTION]: The skill processes external workflow logs, which constitutes a potential surface for indirect prompt injection.
  • Ingestion points: Workflow logs and metadata accessed via the GitHub REST API (SKILL.md).
  • Boundary markers: No explicit delimiters are used to separate untrusted log content from agent instructions.
  • Capability inventory: The skill possesses write capabilities including re-running, cancelling, and triggering workflows via gh api.
  • Sanitization: The instructions do not mention sanitizing or escaping the content of logs before the agent processes them for triage.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 05:34 AM
Security Audit — agent-trust-hub — actions-manager