knowledge-search

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes Bash to execute composio CLI commands for searching Notion pages and retrieving markdown content. These operations are core to the skill's functionality.
  • [SAFE]: The skill processes external data from Notion and user inputs. 1. Ingestion points: User topic and Notion page content. 2. Boundary markers: None explicitly defined. 3. Capability inventory: Bash execution of composio commands. 4. Sanitization: None. While this creates an indirect prompt injection surface, it is standard for knowledge retrieval skills and restricted by the disable-model-invocation setting which enforces the specific search workflow.
  • [SAFE]: No credential exposure, obfuscation, or unauthorized data exfiltration patterns were detected. All external references point to the vendor's official domain.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 08:13 PM
Security Audit — agent-trust-hub — knowledge-search