pbi-challenge

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected. The skill's operations are restricted to reading project documentation and generating analysis reports.
  • [PROMPT_INJECTION]: The skill processes untrusted content from PBI drafts located in the team-artifacts/pbis/ directory. While this serves as an ingestion point for indirect prompt injection, the risk is mitigated by the skill's lack of high-privilege capabilities (like network access or command execution) and its 'human-in-the-loop' design, which requires a human reviewer to validate all AI-generated verdicts and prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 07:25 AM
Security Audit — agent-trust-hub — pbi-challenge