design-training-program

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines an ingestion surface for untrusted data, which presents a risk of indirect prompt injection.
  • Ingestion points: The skill processes 'Existing training materials or curricula' and 'Competency gaps' as optional inputs in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to differentiate between the agent's core instructions and the external data being processed.
  • Capability inventory: The skill metadata allows high-privilege tools including Bash, Read, Write, Edit, Grep, and Glob.
  • Sanitization: No validation, escaping, or filtering procedures for ingested content are specified in the training design steps.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 07:14 AM
Security Audit — agent-trust-hub — design-training-program