commercial-prospecting

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill contains no executable code or scripts and is made up of markdown documentation.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface.
  • Ingestion points: Processes untrusted data from external websites, LinkedIn, and repositories.
  • Boundary markers: No delimiters or isolation instructions are defined for the retrieved data.
  • Capability inventory: The skill is designed to create and modify local markdown files (prospect-profile.md and commercial-state.md).
  • Sanitization: There is no logic for sanitizing or validating external content before it is used in file operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 09:47 PM