archon

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill directs the agent to execute a local Python script using subprocess.run(['python3', 'scripts/list_knowledge.py', archon_host]) to verify API connectivity and retrieve server metadata.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it processes untrusted data from the Archon API. * Ingestion points: The agent ingests data through search results, document content, and task descriptions retrieved from the user-specified Archon host. * Boundary markers: There are no explicit delimiters or instructions provided to prevent the agent from following malicious commands embedded within the retrieved data. * Capability inventory: The skill possesses capabilities for network operations via the requests library, file system reading for document uploads, and command execution via subprocess. * Sanitization: There is no evidence of sanitization or structural validation performed on the API responses before they are incorporated into the agent's reasoning context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 11:38 AM