clay-to-deepline

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the deepline package globally using npm. It specifies a custom registry URL (https://code.deepline.com/api/v2/npm/), which directs the package manager to fetch code from a non-standard source.
  • [COMMAND_EXECUTION]: The skill provides a series of bash commands to set up the environment, including npm install -g, modifying the local npm prefix, and updating the $PATH variable. It also executes authentication and status commands for the deepline tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to convert Clay table configurations into local scripts. This creates a vulnerability surface where malicious instructions could be embedded within the Clay table data and processed by the agent during the conversion or validation phases.
  • Ingestion points: Clay table configurations are ingested and analyzed to generate scripts (SKILL.md).
  • Boundary markers: None specified in the provided instructions to distinguish between configuration data and instructions.
  • Capability inventory: The skill uses the Skill tool to invoke deepline-gtm and performs file read operations on relative paths (e.g., ../deepline-gtm/recipes/).
  • Sanitization: No explicit sanitization or validation of the input Clay configuration is described in the prompt instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 12:22 PM