apollo-webhooks-events
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API responses and webhook payloads (e.g., contact names, email subjects, and organization data), which represents a theoretical attack surface for indirect prompt injection.
- Ingestion points: Contacts Search API responses in
src/sync/contact-poller.tsand webhook payloads insrc/routes/webhooks/apollo.ts. - Boundary markers: The instructions do not define explicit delimiters to separate external data from system instructions.
- Capability inventory: The skill uses
Read,Write,Edit, andBashcapabilities for integration tasks. - Sanitization: The implementation uses
zodfor strict structural validation of incoming data, which mitigates simple schema confusion attacks. - [EXTERNAL_DOWNLOADS]: The skill utilizes standard, well-known Node.js libraries and connects to the official Apollo.io API infrastructure. These external dependencies are routine and appropriate for the skill's stated purpose.
Audit Metadata