model-data

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes user-provided requirement documents and passes the data between sub-agents without strict boundary markers or sanitization.
  • Ingestion points: The requirement document input is read via file path or text argument in SKILL.md.
  • Boundary markers: The prompt template used to invoke sub-agents in SKILL.md lacks delimiters or explicit instructions to isolate untrusted data from system instructions.
  • Capability inventory: The skill utilizes tool-based file reading and writing capabilities across its agents.
  • Sanitization: There is no evidence of input validation or escaping for the user-provided text before it is interpolated into agent prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 12:59 AM
Security Audit — agent-trust-hub — model-data