create-deepwiki

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard Unix utilities such as find, grep, tree, and cp to perform structural discovery and asset inventory within the scanned codebase.
  • [COMMAND_EXECUTION]: The skill executes a suite of local Python utility scripts (validate_docs.py, verify_source_refs.py, and deepwiki_cli.py) to manage documentation validation, source-code grounding, and publishing tasks.
  • [DATA_EXFILTRATION]: The skill contains a dedicated publishing stage that transmits generated documentation to a remote server. While this involves sending codebase details (including code snippets and architectural descriptions) over the network, it is the primary intended function of the skill and targets a user-specified endpoint.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 06:05 AM
Security Audit — agent-trust-hub — create-deepwiki