geo-optimizer
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates an indirect prompt injection surface by fetching and processing content from external URLs.
- Ingestion points: The scripts/audit_url.py script (line 64) fetches HTML, robots.txt, and sitemaps from user-provided URLs.
- Boundary markers: The instructions do not define delimiters or warnings to ignore instructions embedded in the crawled data.
- Capability inventory: The skill is authorized to perform repository analysis and implement code changes, and the audit script has network access.
- Sanitization: Content extracted from the page is processed as raw text without sanitization for agent instructions.
- [DATA_EXFILTRATION]: The scripts/audit_url.py script uses urllib.request.urlopen (line 64) to fetch data from any provided URL. This creates a risk of Server-Side Request Forgery (SSRF), where an attacker-controlled site or a malicious prompt could trick the agent into accessing internal network resources or metadata services.
- [COMMAND_EXECUTION]: The skill explicitly instructs the agent to run a local Python script scripts/audit_url.py via the command line to perform website audits.
Audit Metadata