teach-impeccable

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it synthesizes untrusted project data and user responses into instructions persisted in CLAUDE.md and .impeccable.md. 1. Ingestion points: project files (README, docs, components) and AskUserQuestion output. 2. Boundary markers: Absent. 3. Capability inventory: Writes and updates local files. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 05:34 AM
Security Audit — agent-trust-hub — teach-impeccable