wait-what
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides natural language instructions for communication refinement, encouraging the use of ASD-STE100 Simplified Technical English. It does not execute code, perform network operations, or access sensitive files.
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to read local project files, specifically
CONTEXT.mdandCONTEXT-MAP.md, to incorporate 'ubiquitous language' into its response. - Ingestion points: Local documentation files (
CONTEXT.md,CONTEXT-MAP.md). - Boundary markers: Not present.
- Capability inventory: None; the skill uses
disable-model-invocation: trueand contains no code or tool calls. - Sanitization: None.
Audit Metadata