account-health-audit
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using the
clayCLI (e.g.,clay whoami,clay workflows actions list) to verify the user's workspace environment and retrieve a catalog of available enrichment actions. - [EXTERNAL_DOWNLOADS]: The skill fetches data from various external enrichment providers (referred to as 'arms') such as Clearbit, Owler, Leadmagic, and others through the Clay platform to re-derive account information for verification.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests untrusted account data from CRM exports or list files.
- Ingestion points: CRM fields (domain, company name, headcount, revenue) are read from user-provided lists or exports.
- Boundary markers: The skill does not explicitly use delimiters for these values in prompts, though it uses them primarily as parameters for API calls.
- Capability inventory: The skill has the capability to execute shell commands (
clayCLI) and perform network operations via Clay enrichment actions. - Sanitization: The skill implements normalization for case, spacing, punctuation, and legal suffixes to standardize values before comparison.
Audit Metadata