teach-back-evaluator

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No hardcoded credentials, unauthorized network operations, or malicious file access patterns were identified in the skill content.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its handling of user-provided data.
  • Ingestion points: The variables concept_to_teach and context from the input_schema are interpolated directly into the system prompt in SKILL.md.
  • Boundary markers: No delimiters (such as XML tags, triple quotes, or block separators) or "ignore embedded instructions" warnings are used to isolate user-provided content.
  • Capability inventory: The skill does not request any allowed-tools and does not contain any code for subprocess execution, network requests, or file system modifications.
  • Sanitization: No sanitization or validation of the input strings is performed before interpolation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 11:56 AM
Security Audit — agent-trust-hub — teach-back-evaluator