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) usingpython3to manage state, resolve configurations, and record run metrics. - [COMMAND_EXECUTION]: Employs shell functions like
probe_pluginandresolve_market_config_scriptto 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-curatoragents via theTasktool. 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