event-planning-timeline

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data via an interview workflow in SKILL.md. Boundary markers are established by the requirement to deliver output section-by-section for user validation. The capability inventory reveals only text generation and planning logic, with no subprocess calls, file writing, or network operations. No explicit sanitization is performed, but the lack of dangerous tools keeps the risk low.
  • [SAFE]: The skill consists entirely of markdown instructions. No obfuscation, data exfiltration, or persistence mechanisms were detected. All external skill references belong to the author's own namespace.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 09:13 PM
Security Audit — agent-trust-hub — event-planning-timeline