inclusive-design-orchestrator

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill accepts several user-provided text inputs and interpolates them directly into the agent instructions without structural delimiters or boundary markers.
  • Ingestion points: User-supplied data in fields such as lesson_or_unit, inclusion_challenge, context, known_learner_needs, and existing_plan are directly inserted into the orchestration prompt template in SKILL.md.
  • Boundary markers: Absent. The prompt template does not use delimiters (e.g., triple quotes, XML-style tags, or block markers) to separate user data from instructions, nor does it include explicit directives for the agent to ignore embedded instructions within the input data.
  • Capability inventory: The skill is designed for educational workflow coordination and text generation. It does not exhibit risky capabilities such as shell command execution, file system modification, or non-whitelisted network access.
  • Sanitization: There is no evidence of input validation, escaping, or sanitization logic to mitigate the risk of malicious instructions within the user-provided content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 11:56 AM
Security Audit — agent-trust-hub — inclusive-design-orchestrator