geo-schema
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local Python script located at ~/.claude/skills/geo/scripts/fetch_page.py to retrieve and parse web content.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through external data processing. \n- Ingestion points: HTML and JSON-LD metadata fetched from external URLs via the fetch_page.py script. \n- Boundary markers: The skill lacks instructions to isolate or ignore instructions that might be embedded in the fetched website data. \n- Capability inventory: The agent has access to the Bash and Write tools, which could be abused if the agent is misled by injected content. \n- Sanitization: No sanitization or validation of text content within the fetched metadata is performed before agent analysis.
Audit Metadata