knowledge-generate

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes npx skills add to install additional tools and extensions into the agent's local environment based on the configuration found in the project manifest.
  • [EXTERNAL_DOWNLOADS]: Functional extensions are fetched from the author's GitHub repository (paucasanellas/knowledge.md) during the synchronization process.
  • [PROMPT_INJECTION]: The skill processes natural language instructions in the body of the KNOWLEDGE.md file, treating them as binding configuration rules for its generation logic.
  • Ingestion points: The Markdown body of the KNOWLEDGE.md manifest (Paso 6).
  • Boundary markers: The skill does not define specific delimiters for separating user content from instructions in the manifest body, though it requires user confirmation for non-read-only commands.
  • Capability inventory: Writing to the file system (creating hubs and folders), executing shell commands via npx, and modifying agent memory files (CLAUDE.md and AGENTS.md).
  • Sanitization: No specific sanitization or filtering logic is described for the instructions interpreted from the Markdown body.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 02:57 PM
Security Audit — agent-trust-hub — knowledge-generate