tailor-sdk
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (LOW): This skill instructs the agent to ingest and follow information from external documentation files, creating an indirect prompt injection surface (Category 8). \n- Ingestion points:
node_modules/@tailor-platform/sdk/README.mdand multiple files in thedocs/directory. \n- Boundary markers: The skill does not define delimiters or provide warnings to disregard embedded instructions in the docs. \n- Capability inventory: While the skill is markdown-only, it facilitates tasks like service configuration and CLI execution. \n- Sanitization: No sanitization or validation of documentation content is mentioned.
Audit Metadata