explaining-complex-concepts
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local Node.js scripts, specifically
scripts/generate-explanation.js,scripts/create-analogy.js, andscripts/find-resources.js, to automate the generation of educational content and resource lists. - [EXTERNAL_DOWNLOADS]: The "Resource Curation Strategy" involves searching for and referencing external content from the web, including articles, videos, and interactive tools from third-party domains.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface. It processes external concepts and curated web data that are then interpolated into structured explanation frameworks. There is a lack of explicit boundary markers or sanitization logic in the instructions to prevent malicious instructions embedded in the source material from being executed or obeyed by the agent. Ingestion points include user-provided concepts and web content fetched via the resource discovery script. Capability inventory includes script execution and file writing.
Audit Metadata