cognitive-load-analyser
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, obfuscation, or safety bypass patterns were identified in the skill instructions or metadata. The behavior is consistent with the described educational purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from multiple sources, representing a theoretical injection surface.
- Ingestion points: User-provided learning tasks, materials, and student profiles are interpolated directly into the system prompt in
SKILL.md. - Boundary markers: Data fields are separated by markdown headers, but the prompt does not utilize strict delimiters or specific instructions to ignore embedded commands.
- Capability inventory: The skill has no dangerous capabilities enabled; it does not have access to tools for network communication, file system modification, or command execution.
- Sanitization: There is no evidence of validation or sanitization of the input content.
- Risk Assessment: Because the skill has no actionable capabilities, the risk of a successful indirect prompt injection causing harm is negligible.
Audit Metadata