find-work-phone
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to retrieve configuration guidelines from the vendor's official GitHub repository (
https://raw.githubusercontent.com/clay-run/agent-plugins/main/GETTING_STARTED.md). This is a legitimate resource used for setting up the required environment. - [COMMAND_EXECUTION]: The skill utilizes the
clayCLI for operational tasks, including checking the current user session (clay whoami), listing available enrichment functions (clay functions list), and managing routines. These shell commands are essential for the skill's stated purpose of lead enrichment. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted external data in the form of LinkedIn profiles and contact information.
- Ingestion points: LinkedIn URLs, names, company names, and email addresses sourced from external inputs (SKILL.md).
- Boundary markers: The skill lacks explicit prompt delimiters but requires the agent to verify the correct profile before proceeding with the lookup.
- Capability inventory: Shell command execution via the
clayCLI and reading of local answer files. - Sanitization: No specific sanitization techniques are described for the input strings before they are processed by the CLI tool.
- [SAFE]: The skill contains comprehensive safety constraints, including prohibitions on fabricating data, mandatory credit cost approvals, and explicit warnings against dialing or texting contacts without user consent.
Audit Metadata