apollo-cost-tuning
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes data from the external Apollo.io API, which represents an indirect prompt injection surface. Data retrieved, such as lead names or company info, could potentially contain malicious instructions.
- Ingestion points: Data ingestion occurs through
apollo.searchPeopleandapollo.enrichPersonmethods described in the logic. - Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between its instructions and retrieved data.
- Capability inventory: The skill allows powerful tools including
Read,Write,Edit, andBash, which could be exploited if an injection occurs. - Sanitization: There is no evidence of sanitization or validation of the API response data before processing.
Audit Metadata