skills/tailor-platform/sdk/tailor-sdk/Gen Agent Trust Hub

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.md and multiple files in the docs/ 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
Risk Level
SAFE
Analyzed
Feb 20, 2026, 02:52 AM