udl-lesson-auditor
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates untrusted user data (lesson plans and learner contexts) directly into the system prompt without using boundary markers or sanitization.\n- Ingestion points: Untrusted data enters the agent context via the lesson_plan, learner_context, specific_concerns, and constraints variables in SKILL.md.\n- Boundary markers: The prompt lacks delimiters (such as XML tags or triple quotes) to encapsulate input variables and does not include instructions for the model to ignore embedded commands within the input.\n- Capability inventory: The skill is restricted to text generation; it does not have tool access, file system permissions, network capabilities, or subprocess execution rights.\n- Sanitization: No input validation, escaping, or filtering is performed on the external content before it is processed by the model.\n- [NO_CODE]: The skill consists entirely of markdown instructions and metadata; it does not include or execute any external scripts, binaries, or code files.
Audit Metadata