afk-implement-tasks

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses ticket files as a 'source of truth' for implementation instructions. This creates an indirect prompt injection surface where instructions embedded in project tickets (like Acceptance Criteria or Handoff Notes) could influence the agent's behavior.
  • Ingestion points: Ticket files (referenced in SKILL.md and references/resume.md).
  • Boundary markers: None specified; the skill does not instruct the agent to distinguish between its core logic and instructions found within ticket data.
  • Capability inventory: The skill is designed to modify repository source code based on ticket contents.
  • Sanitization: No sanitization or validation of the contents of the ticket files is performed before the agent follows their instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 04:58 AM
Security Audit — agent-trust-hub — afk-implement-tasks