afk-to-tickets

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves context from external issue URLs and local specification paths. It integrates with well-known services like GitHub and Linear for ticket publishing.
  • [PROMPT_INJECTION]: The skill processes untrusted data from external artifacts and conversation history, which presents a surface for indirect prompt injection.
  • Ingestion points: Fetches the full body and comments from external issue URLs and local specification files as defined in SKILL.md.
  • Boundary markers: There are no specific delimiters or instructions defined to prevent the agent from following instructions embedded within the ingested data.
  • Capability inventory: The skill can perform codebase exploration, write local checkpoint files, and publish new issues to external trackers.
  • Sanitization: The instructions do not define any sanitization or validation logic for data retrieved from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 02:52 PM
Security Audit — agent-trust-hub — afk-to-tickets