indexability
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local validation script 'scripts/score.py' using the python3 interpreter.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from URLs which could contain malicious instructions. Ingestion points: Data from a user-provided URL, specifically robots.txt, sitemap, and status codes. Boundary markers: The agent is guided by a manual checklist that separates data recording from validation. Capability inventory: The skill utilizes local command execution (python3). Sanitization: No explicit sanitization of the fetched URL content is described.
Audit Metadata