udl-lesson-auditor
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied lesson plans which represents a potential attack surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context through the
lesson_plan,learner_context, andspecific_concernsinput fields inSKILL.md. - Boundary markers: The prompt uses simple text labels (e.g.,
Lesson plan: {{lesson_plan}}) to separate user input from instructions, but lacks strict structural delimiters like XML tags or triple-backticks to prevent the LLM from confusing data with commands. - Capability inventory: The skill has no active capabilities; it does not utilize
allowed-tools, shell commands, file writing, or network operations. - Sanitization: There is no evidence of input validation or sanitization to filter out malicious instructions embedded within the lesson plan data.
Audit Metadata