apollo-lead-finder
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes lead and contact information retrieved from the external Apollo.io API, creating an attack surface for indirect instructions.
- Ingestion points: External data is retrieved through
scripts/apollo_client.pyvia the search and enrichment API endpoints. - Boundary markers: While the skill documentation requires user confirmation before key actions, it does not use explicit boundary markers to prevent the agent from following instructions embedded in the API data.
- Capability inventory: The skill performs network operations (Apollo API), file system writes (CSV export), and CRM operations (Apollo list/contact creation).
- Sanitization: API response data is processed without specific sanitization before presentation to the user or inclusion in exports.
- [EXTERNAL_DOWNLOADS]: The skill interacts with the Apollo.io API to fetch lead data and supports routing requests through a vendor-provided proxy at
api.gooseworks.aiwhen configured. These communications include the necessary API keys for service authentication.
Audit Metadata