tsg-flow-techspec-creator

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines a documentation process without code execution or network exfiltration. It explicitly instructs the agent to avoid inventing information and to acknowledge uncertainties. It further improves security by requiring explicit documentation for sensitive data handling.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted PRD files and UI mockups to generate documentation. While this is an ingestion point for untrusted data, the risk is limited by the skill's rigid documentation format and instructions. Ingestion points: prd.md, contracts.md, and Figma/mockup files. Boundary markers: Absent for external content. Capability inventory: File creation and modification of markdown files. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 05:33 PM