skills/clawlink-hq/skills/affinity/Gen Agent Trust Hub

affinity

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the @useclawlink/cli tool to perform all operations, including authentication (login), service connection (connect), and data manipulation (run). These commands are executed via the system shell.
  • [EXTERNAL_DOWNLOADS]: Uses npx to execute the @useclawlink/cli package. This involves downloading the package from the public npm registry at runtime if it is not present in the local cache.
  • [CREDENTIALS_UNSAFE]: The skill notes that authentication tokens are stored locally in the user's home directory at ~/.clawlink/credentials.json. This is a standard mechanism for CLI tools to persist session data between commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves data from Affinity (e.g., list entries, person details, company info). This data is external and untrusted. While the skill instructs the agent to confirm before writing data, the ingestion of CRM content represents a standard surface for indirect prompt injection if that content contains malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — affinity