geo-schema
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to use the Bash tool to execute a Python script (
fetch_page.py) located at a specific local path:~/.claude/skills/geo/scripts/fetch_page.py. This script is used to fetch and parse external web content by taking a URL as a command-line argument.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external websites, creating a potential attack surface where malicious instructions could be embedded in the HTML or JSON-LD of the target pages. - Ingestion points: Untrusted data is ingested from external URLs via the
fetch_page.pyscript and theWebFetchtool. - Boundary markers: The skill instructions do not define specific delimiters or warnings to ignore instructions found within the fetched content.
- Capability inventory: The skill has access to powerful tools including
Bash,Write, andWebFetch, which could potentially be abused if the agent follows instructions hidden in the data it processes. - Sanitization: There are no explicit instructions for sanitizing or filtering the fetched content before the agent parses and acts upon it.
Audit Metadata