tsg-flow-vision-creator

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary function is the creation of strategic documentation based on a provided template (templates/vision-template.md). It operates entirely on local files such as vision.md and flow-state.json.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an ingestion surface by reading user-provided context and existing strategic documents (Ingestion point: SKILL.md). Its capabilities are limited to writing structured text to markdown and JSON files (Capability inventory: vision.md, flow-state.json). No explicit boundary markers or sanitization processes for the ingested data are defined. However, as the skill does not generate executable code or perform network operations, the risk of exploiting this surface is negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 06:41 PM