specialist-project-management-project-management-project-shipper

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill interpolates untrusted user input directly into a sub-agent prompt using the {the_user_question} variable without defined boundary markers or instructions to ignore embedded commands. This creates a surface for indirect prompt injection where a user input could potentially influence the sub-agent's behavior beyond its intended persona.
  • Ingestion points: {the_user_question} in SKILL.md.
  • Boundary markers: Absent. The input is appended directly to the end of the sub-agent prompt.
  • Capability inventory: Spawns sub-agents via the Agent tool.
  • Sanitization: Absent. There is no evidence of filtering or escaping of the user-provided string.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:50 PM
Security Audit — agent-trust-hub — specialist-project-management-project-management-project-shipper