knowledge-curate

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes several internal Python scripts (e.g., knowledge-binding.py, get-market-config.py, wiki-coverage.py, candidate-store.py, run-metrics.py) using python3 to manage state, resolve configurations, and record run metrics.
  • [COMMAND_EXECUTION]: Employs shell functions like probe_plugin and resolve_market_config_script to dynamically verify the presence of sibling plugins and locate script paths within the local plugin environment.
  • [EXTERNAL_DOWNLOADS]: Orchestrates the retrieval of external information by dispatching source-curator agents via the Task tool. These sub-agents are responsible for performing web searches and fetching remote content into a shared cache.
  • [PROMPT_INJECTION]: The skill processes project plans (plan.json) which contain user-influenced data (topics, sub-questions). While it defines the workflow, it relies on the dispatched agents and underlying scripts to handle data sanitization and instruction boundaries.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 01:51 PM
Security Audit — agent-trust-hub — knowledge-curate