wait-what
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to ingest content from project-specific files (
CONTEXT.md,CONTEXT-MAP.md) to guide its response style. - Ingestion points: Processes repository files named
CONTEXT.mdandCONTEXT-MAP.mdat runtime. - Boundary markers: No specific delimiters or instructions to ignore embedded commands within those files are provided.
- Capability inventory: The skill is restricted via
disable-model-invocation: true, which prevents the agent from calling tools or executing code, significantly limiting the potential impact of any injected instructions. - Sanitization: No sanitization or validation of the context file content is performed.
Audit Metadata