apollo
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: Uses standard curl commands to interact with the Apollo.io REST API for searching and enriching contact data.
- [DATA_EXFILTRATION]: Performs network operations solely to the official api.apollo.io domain, which is a well-known B2B sales intelligence service. No sensitive local files or environment data are accessed or transmitted.
- [CREDENTIALS_UNSAFE]: Correctly utilizes environment variables ($APOLLO_TOKEN) for API authentication, avoiding the use of hardcoded secrets and following standard practice for secret management.
- [PROMPT_INJECTION]: The skill processes data retrieved from the Apollo.io API (such as contact names, job titles, and company descriptions), which constitutes an indirect prompt injection surface. 1. Ingestion points: Data enters the agent context through the search and match API responses from api.apollo.io. 2. Boundary markers: No explicit boundary markers or 'ignore' instructions are defined in the provided skill text to delimit external data. 3. Capability inventory: The skill enables network requests via curl and local data processing/display. 4. Sanitization: No specific sanitization or validation of external API content is described in the skill. However, the risk is deemed minimal due to the structured nature of the B2B data and the reputation of the source.
Audit Metadata