udl-barrier-anticipator
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied content (task descriptions and learner profiles) through the
task_descriptionandlearner_variabilityfields. - Ingestion points: User inputs are interpolated directly into the prompt in
SKILL.mdusing the{{task_description}}and{{learner_variability}}placeholders. - Boundary markers: The prompt does not use explicit boundary markers (e.g., XML tags or unique delimiters) to separate instructions from user-provided data.
- Capability inventory: The skill has no execution tools, file system access, or network capabilities. It only generates a structured text analysis.
- Sanitization: There is no evidence of input validation or sanitization before processing. While the attack surface exists, the lack of capabilities makes this a low-risk concern.
Audit Metadata