Skills
Navigate
skills/clay-run/clay-skill-creator/clean-and-refresh-contact-data/Gen Agent Trust Hub

clean-and-refresh-contact-data

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes contact information from user-provided CSV or CRM exports, creating a surface for potential injection of instructions via data fields.
  • Ingestion points: The user-supplied CSV or CRM export list (SKILL.md, Step 1).
  • Boundary markers: None specified to distinguish data from instructions.
  • Capability inventory: Execution of vendor-specific CLI tools (clay) and network-based enrichment (SKILL.md, Step 0 and Step 2).
  • Sanitization: No data validation or sanitization process is described.
  • [COMMAND_EXECUTION]: The agent is instructed to run shell commands using the clay CLI for environment checks and routine cost verification.
  • Evidence: Commands include clay whoami and clay routines list in SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 03:02 AM