clay-mastery

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references multiple external API endpoints for data enrichment services, such as Prospeo, Findymail, and FullEnrich, intended to be accessed via the ColdIQ marketplace infrastructure.
  • [COMMAND_EXECUTION]: The skill provides JavaScript snippets (Clayscript) for data cleaning, domain extraction, and conditional logic. These operations are restricted to standard string and regex manipulations for use within the Clay platform.
  • [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by defining templates for AI-based company qualification and personalization that incorporate external data fields.
  • Ingestion points: Data ingested during the 'Input' phase, including Company Name, Domain, and LinkedIn URL as described in 'SKILL.md'.
  • Boundary markers: Absent; variables like '{{Signal}}' are interpolated directly into natural language prompts without delimiters.
  • Capability inventory: Capabilities are limited to data enrichment API calls and text generation; no local file system access or shell command execution is provided.
  • Sanitization: No sanitization or validation processes are mentioned for data before it is interpolated into prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 05:07 AM
Security Audit — agent-trust-hub — clay-mastery