typescript-engineering
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill instructions create an indirect prompt injection surface by directing the agent to ingest and analyze external project data.\n
- Ingestion points: Project configuration (tsconfig.json, package.json) and source code files as specified in SKILL.md.\n
- Boundary markers: None identified; the instructions do not specify the use of delimiters or 'ignore' warnings for processed code.\n
- Capability inventory: The agent is directed to use external diagnostic tools and test runners like
tsc,vitest, andjest.\n - Sanitization: No content sanitization or validation of the ingested files is mentioned before processing or tool execution.\n- [NO_CODE]: The skill consists entirely of instructional markdown and configuration files; it does not include or execute its own internal scripts.
Audit Metadata