geo-optimization

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The monitoring script scripts/geo-monitor.py executes local CLI commands via subprocess.run to call the clawdbot tool.
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations to fetch data from the Perplexity AI API (api.perplexity.ai).
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface through its processing of search result data.
  • Ingestion points: The content from Perplexity API results is processed by scripts/geo-monitor.py.
  • Boundary markers: No markers or delimiters are used to wrap external content.
  • Capability inventory: The skill can execute subprocesses and write results to the local filesystem.
  • Sanitization: No filtering or sanitization is applied to the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 08:46 AM