project-manager

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of external data.
  • Ingestion points: External project documentation including the Project Charter, Requirements, and Schedule Plan (SKILL.md).
  • Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands within the provided documents.
  • Capability inventory: Writing project, risk, and meeting reports to local filesystem paths (SKILL.md).
  • Sanitization: Absent; the skill does not mandate validation or escaping of external data before its inclusion in outputs.
  • [NO_CODE]: The skill contains no executable scripts or external code dependencies; it consists entirely of markdown documentation and templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 01:41 PM
Security Audit — agent-trust-hub — project-manager