lw-lms-abilities
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill acts as a reference for the LW LMS Abilities API, providing documentation on tool usage and API interaction patterns. The instructions focus on legitimate administration and auditing tasks within a WordPress environment.
- [INDIRECT_PROMPT_INJECTION]: The skill enables an agent to ingest and manipulate external LMS data. While this is the intended functionality, it introduces an indirect prompt injection surface. 1. Ingestion points: API responses from lw-lms/list-courses, lw-lms/get-course, and lw-lms/get-progress in SKILL.md. 2. Boundary markers: The skill does not explicitly define delimiters for separating external data from instructions. 3. Capability inventory: The skill allows updating learner progress via the lw-lms/set-progress ability. 4. Sanitization: No specific sanitization or validation of the retrieved LMS content is prescribed in the skill instructions.
- [EXTERNAL_DOWNLOADS]: The skill references the official GitHub repository for the LW LMS plugin and standard WordPress developer documentation. These references are appropriate for the skill's purpose and originate from well-known services.
Audit Metadata