ai-learning-boundary-mapper
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data via the
assignment_descriptionandlearning_objectivesfields which are interpolated directly into the system prompt. - Ingestion points:
assignment_descriptionandlearning_objectivesfields inSKILL.mdprompt section. - Boundary markers: Absent; the user input is placed directly after labels (e.g.,
**Assignment description:** {{assignment_description}}) without delimiters to prevent the model from following instructions contained within the input. - Capability inventory: The skill has no dangerous capabilities; it performs only text analysis and does not have access to the filesystem, network, or shell tools.
- Sanitization: Absent; the skill does not filter or validate the input content for instructional patterns.
Audit Metadata