terse-create
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection as it processes untrusted workspace data and user arguments to generate new workflow logic. This is an expected behavior for a code-generation tool.
- Ingestion points: The skill reads local files including
src/terse.generated.tsandsrc/terse.jobs.ts, and accepts user input via the$ARGUMENTSvariable inSKILL.md. - Boundary markers: The instructions do not explicitly mandate the use of delimiters or 'ignore' instructions when reading workspace content, though the intent is technical context retrieval.
- Capability inventory: The agent is authorized to execute the
terseCLI, write files to the project structure, and spawn specialized research subagents. - Sanitization: The instructions focus on technical accuracy and type safety but do not include specific sanitization or filtering logic for instructions that might be embedded in ingested workspace files.
Audit Metadata