retrieval-practice-generator
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill incorporates strong defensive instructions to mitigate potential prompt injection from user-provided content. It explicitly directs the agent to treat all input text (curriculum, notes, links) as untrusted data and to ignore any commands or directives embedded within that material.- [DATA_EXFILTRATION]: The skill establishes privacy boundaries, instructing the agent to minimize learner context and avoid exposing identifiable student data in the output. It also forbids the agent from contacting external services based on input directives.- [NO_CODE]: The skill consists entirely of markdown instructions and metadata. It does not include executable scripts, configuration for external tools, or remote package dependencies.- [SAFE]: All cited external links in the documentation are for attribution and licensing purposes (Creative Commons and GitHub source citation) and do not involve runtime execution or automated data fetching.
Audit Metadata