inclusive-design-orchestrator
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to provide inclusive design recommendations.
- Ingestion points: The skill accepts untrusted data through the 'lesson_or_unit', 'inclusion_challenge', 'context', 'known_learner_needs', 'existing_plan', and 'constraints' fields defined in the input_schema of SKILL.md.
- Boundary markers: Absent; the prompt interpolates these user-provided variables directly into the system instructions without using specific delimiters or 'ignore' warnings to prevent the model from obeying instructions embedded in the data.
- Capability inventory: No executable code, network operations, subprocess calls, or sensitive file system access capabilities are present in the skill or its associated instructions. The skill is limited to generating text-based advice and routing between other educational skills.
- Sanitization: Absent; there is no evidence of escaping, validation, or filtering for the content ingested from the external input fields.
Audit Metadata