apollo
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
curlcommand to interact with the Apollo.io API for data enrichment. - [EXTERNAL_DOWNLOADS]: The skill connects to the domain
api.apollo.io. As Apollo.io is a well-known service for sales intelligence, this interaction is considered safe and is required for the skill's primary functionality. - [PROMPT_INJECTION]: The skill processes user-supplied LinkedIn URLs, which represents a surface for indirect prompt injection.
- Ingestion points: User-provided URLs are ingested in
people-enrichment/SKILL.md. - Boundary markers: The skill includes a validation step ensuring URLs start with
https://www.linkedin.com/in/. - Capability inventory: The skill is restricted to making network calls via
curlto a specific API. - Sanitization: Input data is URL-encoded before being used in the shell command, which provides protection against command injection.
Audit Metadata