elaborative-interrogation-generator
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by ingesting untrusted data through multiple input variables used to calibrate the generated educational content.
- Ingestion points: The variables
{{content_text}},{{prior_knowledge}},{{learning_objectives}}, and{{student_profiles}}inSKILL.mdare populated with external data. - Boundary markers: Absent; the user-provided or context-engine-provided text is interpolated directly into the instructions for the model.
- Capability inventory: The skill does not have any dangerous capabilities; it does not invoke shell commands, perform network requests, or write to the file system.
- Sanitization: Absent; the skill relies on the model's inherent ability to distinguish instructions from content.
- Note: This is an architectural observation rather than a vulnerability, as the skill lacks any privileged tools that an attacker could exploit through injection.
Audit Metadata