teach-impeccable

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is designed for one-time project setup, reading common developer files like package.json and README.md to assist with design consistency.
  • [PROMPT_INJECTION]: The skill presents an indirect injection surface because it ingests data from untrusted codebase files and incorporates it into persistent instruction files.
  • Ingestion points: The skill reads various project files including README.md, package.json, and component source code.
  • Boundary markers: The instructions do not define delimiters or specific markers to isolate ingested content from the system prompt.
  • Capability inventory: The skill utilizes file read capabilities across the codebase and file write access to .impeccable.md and .github/copilot-instructions.md.
  • Sanitization: There is no evidence of sanitization or filtering applied to the ingested content before it is persisted in configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 12:51 PM
Security Audit — agent-trust-hub — teach-impeccable