corroboration-skill-builder
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines an input schema that accepts strings for historical topics and student levels which are interpolated directly into the model instructions. This creates a potential surface for indirect prompt injection where a user could attempt to override agent behavior. The risk is significantly mitigated because the skill does not utilize any scripts or dangerous tools.
- Ingestion points: The input_schema fields historical_topic, student_level, and current_challenge in SKILL.md.
- Boundary markers: Absent; user inputs are placed directly after bolded labels.
- Capability inventory: No executable scripts, network operations, or tool invocations are present in the skill files.
- Sanitization: No input validation or escaping mechanisms are implemented.
Audit Metadata