apollo-core-workflow-a

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill is designed to retrieve and process contact data including names, emails, and phone numbers. This exposure is consistent with the primary purpose of a lead generation tool and is not indicative of malicious exfiltration.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests data from external sources (the Apollo API) and passes it into the agent's context.
  • Ingestion points: External data is ingested in src/services/apollo/people-search.ts, src/services/apollo/company-enrichment.ts, and src/services/apollo/contact-enrichment.ts.
  • Boundary markers: None identified in the provided code snippets to delimit API content from agent instructions.
  • Capability inventory: The skill has access to Write (file system) and Bash (command execution) via allowed tools.
  • Sanitization: No specific sanitization or filtering of API response strings (e.g., company descriptions or person titles) is implemented before data transformation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 11:57 PM