sales-prospecting

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to third-party service providers including Fiber AI (api.fiber.ai), Hunter, and Abstract Company Enrichment via the mpp.paywithlocus.com gateway. These connections are necessary for the skill's core functionality of data retrieval and lead enrichment.
  • [COMMAND_EXECUTION]: The instructions and examples specify the use of the selat CLI and selat-pay utility to execute the prospecting pipeline and manage payments via the SELAT Router.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating user-provided parameters directly into JSON request bodies for external API calls.
  • Ingestion points: User-supplied parameters such as companyQuery, jobTitles, and domain defined in manifest.json.
  • Boundary markers: None; parameters are inserted directly into the JSON structure for the API payload.
  • Capability inventory: Performs network POST operations to external endpoints via the payment router.
  • Sanitization: There is no evidence of input validation or escaping for the interpolated strings within the provided manifest configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 07:34 PM
Security Audit — agent-trust-hub — sales-prospecting