email-campaign

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill performs network operations to external lead enrichment and verification services.
  • Requests are made to api.fiber.ai, hunter.mpp.paywithlocus.com, apollo.mpp.paywithlocus.com, and abstract-company-enrichment.mpp.paywithlocus.com to fetch outreach data.
  • These operations are documented as the primary function of the skill and utilize a specific payment protocol (MPP on Tempo).
  • [PROMPT_INJECTION]: The skill features a data ingestion surface where user-provided inputs are interpolated into network request bodies.
  • Ingestion points: User parameters including domain, email, firstName, lastName, and company are defined in manifest.json and SKILL.md.
  • Boundary markers: User inputs are encapsulated within structured JSON objects in the manifest steps, providing a layer of separation from the command structure.
  • Capability inventory: The skill utilizes network POST requests to external APIs; it does not perform local file writes or shell command execution beyond the payment tool.
  • Sanitization: The manifest relies on template interpolation (${variable}); specific input validation is handled by the execution environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 07:34 PM
Security Audit — agent-trust-hub — email-campaign