teach
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
lsandmkdirshell commands to discover and organize learning progress files within the~/.skulto/teach/directory. These operations are essential for its state management functionality and are appropriately scoped to a local data folder. - [PROMPT_INJECTION]: By processing user-supplied documents to generate curriculum and assessments, the skill creates an indirect prompt injection surface. While no specific malicious instructions were found in the skill's own code, it does not specify sanitization protocols or boundary markers for the data it ingests from external files.
Audit Metadata