people-property

Warn

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the 'agentcash' package from the public npm registry, which is an external dependency from a source not listed as a trusted vendor.
  • [REMOTE_CODE_EXECUTION]: The use of 'npx agentcash@latest' involves downloading and executing remote code at runtime, which introduces a supply chain risk if the package is compromised.
  • [DATA_EXFILTRATION]: Sensitive search data is sent to 'stableenrich.dev', and the skill retrieves sensitive Personal Identifiable Information (PII) such as home addresses and phone numbers, which constitutes a risk of data exposure.
  • [COMMAND_EXECUTION]: The skill performs shell command execution via 'npm' and 'npx' to set up the environment and fetch data.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion points: API response data from 'stableenrich.dev' in SKILL.md. Boundary markers: None. Capability inventory: 'npx agentcash' for network data fetching. Sanitization: No evidence of data validation or sanitization before processing API outputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 19, 2026, 11:23 AM