vzdelavaci-metodiky

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a didactic framework for building educational apps, providing instructions on pedagogical methods like Socratic learning and the Feynman technique.- [CREDENTIALS_UNSAFE]: The skill actively promotes secret management best practices. In references/ai-provoz.md, it explicitly instructs developers to never include API keys in client-side code and to handle authentication only on protected server-side infrastructure.- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates high security awareness regarding untrusted data. It provides guidelines in references/ai-provoz.md to treat all user-supplied inputs and model responses as untrusted, recommending architectural protections and 'cognitive pauses' for students to verify AI output before use.- [EXTERNAL_DOWNLOADS]: Installation instructions in README.md and docs/POUZITI.md use the standard npx skills add command referencing the author's own GitHub repository (siberius/learning-methodologies), which is consistent with the provided author metadata and represents expected vendor functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 11:04 AM