k12-lesson-prep

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill is designed to analyze K-12 lesson tasks provided by external sources. As with any skill that processes external text, there is a potential for the content to contain instructions intended to influence the agent's behavior.
  • Ingestion points: The skill ingests 'the actual lesson' content as described in SKILL.md.
  • Boundary markers: The instructions do not include explicit delimiters to help the agent distinguish between lesson data and its internal instructions.
  • Capability inventory: The skill is authorized to write its analysis to a preparation note at $OUTPUT_DIR/prep_note.md.
  • Sanitization: No specific steps for sanitizing or filtering the ingested lesson content are defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 01:39 AM
Security Audit — agent-trust-hub — k12-lesson-prep