find-work-email
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides a link to setup documentation hosted on the vendor's official GitHub repository at
https://raw.githubusercontent.com/clay-run/agent-plugins/main/GETTING_STARTED.md. This is a standard reference for plugin configuration. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data, specifically LinkedIn URLs, names, and company domains, to perform email lookups.
- Ingestion points: LinkedIn URLs and profile data are processed in
SKILL.md(Step 1). - Boundary markers: None explicitly defined for input strings.
- Capability inventory: The skill uses
clayCLI tools for network-based lookups and mailbox probes (Step 3 and Step 4). - Sanitization: No input sanitization is mentioned, though the skill performs output validation (MX checks and role address filtering).
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
clayCLI tools (e.g.,clay whoami,clay routines list,clay routines runs start). These commands are essential for the skill's stated purpose of interacting with the Clay workspace and managed functions.
Audit Metadata