wiki-from-research

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains no instructions designed to bypass safety filters or extract system prompts. Its directives are purely operational and facilitate the orchestration of research and wiki workflows.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool for directory navigation and path resolution. It implements safety controls such as kebab-case slug derivation and collision checks to ensure commands remain within the intended project workspace.
  • [DATA_EXFILTRATION]: No unauthorized data transfer or network operations were identified. The skill's data access is limited to project files and configuration data within the local workspace.
  • [REMOTE_CODE_EXECUTION]: The skill does not download or execute code from external sources. All execution is handled by dispatching tasks to verified internal tools from the same vendor ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 04:41 PM
Security Audit — agent-trust-hub — wiki-from-research