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

apollo

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses npx @useclawlink/cli to interact with Apollo. This command executes the author's official CLI tool to perform searches and manage records.
  • [EXTERNAL_DOWNLOADS]: Core functionality depends on the @useclawlink/cli package downloaded from the NPM registry, which is the vendor's intended distribution method.
  • [CREDENTIALS_UNSAFE]: Access tokens are stored at ~/.clawlink/credentials.json. This is standard behavior for the ClawLink CLI to facilitate persistent sessions without manual API key entry.
  • [DATA_EXFILTRATION]: The skill retrieves records from Apollo (e.g., contacts, deals) and incorporates them into the agent's context. This data ingestion is the primary purpose of the integration.
  • [PROMPT_INJECTION]: As the skill processes external data from Apollo CRM, it possesses a surface for indirect prompt injection. Ingestion point: apollo_* actions; Capability inventory: npx @useclawlink/cli run; Boundary markers and sanitization are not explicitly defined in the instruction file.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — apollo