skills/garethmanning/education-agent-skills/dispositional-knowledge-assessment-designer/Gen Agent Trust Hub
dispositional-knowledge-assessment-designer
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 input from external informants which can potentially be used to influence agent behavior.
- Ingestion points: Data enters the skill context through fields in SKILL.md including existing_observation_data, student_self_assessment_data, parent_input, and school_feedback_structure.
- Boundary markers: Inputs are separated by bold text headers but lack strong delimiters or explicit instructions to disregard embedded commands.
- Capability inventory: The skill produces instructional text and protocols; while no tools are called within the skill file, the generated content is intended for further agent action.
- Sanitization: No sanitization or verification of the external input data is performed.
Audit Metadata