tsg-flow-domain-decomposer
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from a mandatory input file named
vision.md. - Ingestion points: The skill explicitly reads and extracts information from
vision.mdin Phase 1 of its execution flow. - Boundary markers: The instructions lack explicit boundary markers or delimiters when interpolating data from
vision.mdinto the agent's context, making it potentially susceptible to instructions hidden within the input text. - Capability inventory: The skill possesses file-write capabilities, specifically generating
context/domain-map.mdand updating a state tracking fileflow-state.json. - Sanitization: There are no instructions for sanitizing or filtering external content before processing it for domain decomposition.
Audit Metadata