faion-gtm-strategist

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): The skill defines a surface for Indirect Prompt Injection (Category 8) by providing instructions for the agent to process external data without sufficient guardrails.\n
  • Ingestion points: The context discovery framework in SKILL.md directs the agent to read and analyze project files in .aidocs/product_docs/, .aidocs/backlog/, .aidocs/todo/, and docs/ directories.\n
  • Boundary markers: The methodology does not include specific boundary markers or instructions to treat data from these files as untrusted content, which is a standard safety measure for this vector.\n
  • Capability inventory: The skill is configured with a powerful toolset including Read, Write, Edit, Task, WebSearch, and TodoWrite, providing a significant impact surface if an injection attack is successful.\n
  • Sanitization: The instructions lack any data sanitization, escaping, or validation requirements for the information being ingested from the user's project environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:17 PM