clean-email-list
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input data from user-supplied CSV files or tables. 1. Ingestion points: The agent reads and processes email lists as described in Step 1. 2. Boundary markers: There are no specific delimiters or instructions provided to the agent to ignore potentially malicious instructions embedded within the data rows. 3. Capability inventory: The skill can execute shell commands via the Clay CLI, perform file writes for reporting, and interact with external APIs through Clay actions. 4. Sanitization: The instructions do not outline specific sanitization or filtering logic to neutralize potential injection attacks within the input data.
- [COMMAND_EXECUTION]: The skill uses the 'clay whoami' command and a 'setup' skill to verify the environment configuration. These are standard utility calls for the Clay platform.
- [EXTERNAL_DOWNLOADS]: The skill points to configuration and setup guidelines hosted on the author's official GitHub repository ('clay-run'). This is a trusted resource used for environment configuration.
Audit Metadata