leadmagic-cli
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill instructions and associated files define a standard workflow for using a third-party CLI tool.
- [COMMAND_EXECUTION]: The skill includes a local utility script
scripts/check-output.pyintended for validating agent-generated deliverables. This script performs static analysis on text files and does not engage in unsafe operations or external network requests. - [DATA_EXFILTRATION]: The skill manages the processing of CSV data via the LeadMagic CLI. This behavior is consistent with the skill's stated purpose of contact enrichment and involves standard interaction with the service's official command-line interface.
- [PROMPT_INJECTION]: The skill processes external CSV data sources. While this represents a potential surface for indirect prompt injection (Category 8), the risk is inherent to data-processing tasks and the skill does not exhibit unsafe interpolation patterns or instructions that bypass safety constraints.
Audit Metadata