strategy-document

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data provided by the user to generate strategic documents, which constitutes a surface for indirect prompt injection. \n
  • Ingestion points: The context gathering instructions in Step 2 of SKILL.md. \n
  • Boundary markers: No explicit delimiters or warnings to ignore instructions embedded in user data are provided. \n
  • Capability inventory: None; the skill does not instruct the agent to use any tools or execute any shell commands, scripts, or network operations. \n
  • Sanitization: No input validation or sanitization mechanisms are defined. \n- [NO_CODE]: The skill consists exclusively of markdown instructions and templates and does not include any executable scripts or tool configurations.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:27 AM
Security Audit — agent-trust-hub — strategy-document