Apollo Automation
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data (leads, organizations, and contact records) retrieved from Apollo.io, which serves as a potential vector for indirect prompt injection.
- Ingestion points: Data ingested via
APOLLO_ORGANIZATION_SEARCH,APOLLO_PEOPLE_SEARCH, andAPOLLO_SEARCH_CONTACTS(SKILL.md). - Boundary markers: The instructions lack specific delimiters or prompt-level instructions to ignore adversarial content within the retrieved records.
- Capability inventory: The skill provides capabilities for searching, enriching, and updating contact stages within the user's Apollo account (SKILL.md).
- Sanitization: There is no description of data sanitization or validation for content fetched from the external API.
- [EXTERNAL_DOWNLOADS]: The skill requires connecting to the Composio MCP server at
https://rube.app/mcp. This is a standard infrastructure endpoint for the vendor's integration service.
Audit Metadata