geo-fundamentals
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill exhibits a surface for indirect prompt injection as it ingests untrusted project data via
scripts/geo_checker.py(SKILL.md). No boundary markers or sanitization routines are specified. The risk is categorized as LOW because the available tools (Read, Glob, Grep) only allow data retrieval and internal reasoning, preventing active exfiltration or system modification. - [COMMAND_EXECUTION] (LOW): The skill documentation references the local execution of an auditing script. No patterns of arbitrary command execution or privilege escalation were found.
- [DATA_EXFILTRATION] (SAFE): No network operations, hardcoded credentials, or access to sensitive system directories (e.g., SSH keys, cloud credentials) were identified.
Audit Metadata