zfb-wisdom

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local shell commands pnpm format:md and pnpm build within the docs/ directory. These are standard maintenance operations for documentation projects and do not involve suspicious remote connections or elevated privileges.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external data from Markdown files in the docs/ and docs-ja/ directories.
  • Ingestion points: Documentation files in docs/ and docs-ja/ directories.
  • Boundary markers: Absent; the instructions do not specify delimiters for external content.
  • Capability inventory: The agent can perform file writes (creating/updating .mdx files) and execute local shell commands (pnpm).
  • Sanitization: Absent; the agent is instructed to read and apply the information directly from the articles.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 06:09 PM
Security Audit — agent-trust-hub — zfb-wisdom