geo-prospect

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary function is the management of business leads and customer records, which is a legitimate and standard administrative use case.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform routine local file system operations, specifically creating the necessary directory structure for data storage (mkdir -p ~/.geo-prospects/). These operations are consistent with the skill's utility and are restricted to the user's home directory.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. Ingestion points: User-supplied domains, contact information, and notes entered via /geo prospect commands in SKILL.md. Boundary markers: Absent in the JSON serialization and display logic. Capability inventory: The skill has access to Bash and Write tools in SKILL.md for local file management. Sanitization: No input validation or escaping is specified for the stored data. However, the orchestration logic is limited to rendering tables and summaries, and no instructions were found that would lead to the execution of this untrusted data as agent commands.
  • [DATA_EXFILTRATION]: All prospect data and audit files are stored locally within the ~/.geo-prospects/ directory. The skill contains no instructions for establishing network connections or transmitting data to external servers.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 01:48 PM