to-issues

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions define a standard administrative workflow for project management. No evidence of obfuscation, data exfiltration, or malicious instruction overrides was found.
  • [PROMPT_INJECTION]: The skill retrieves content from external issue trackers (Step 1), which presents a surface for indirect prompt injection. However, this is a functional requirement for the skill's purpose and is managed by user-in-the-loop validation (Step 4).
  • Ingestion points: External issue bodies and comments (SKILL.md).
  • Boundary markers: None specified for external data interpolation.
  • Capability inventory: The skill allows the agent to read from and publish to an issue tracker.
  • Sanitization: The skill relies on user approval of the drafted issues before publishing, acting as a manual sanitization step.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 11:17 AM
Security Audit — agent-trust-hub — to-issues