sales-apollo-sequences
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates as a purely instructional guide for configuring the Apollo.io platform.
- [COMMAND_EXECUTION]: Provides an optional installation command (
npx skills add) for related skills. This is a standard workflow for the skill vendor 'sales-skills' and does not involve arbitrary or obscured execution. - [DATA_EXFILTRATION]: No indicators of sensitive data harvesting or unauthorized network transmission were found. The skill focuses on legitimate email configuration and marketing metrics.
- [PROMPT_INJECTION]: No behavioral overrides, safety bypass attempts, or malicious metadata patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill implements a self-improving mechanism via
references/learnings.md. 1. Ingestion point: The file is read during the initial context gathering step. 2. Boundary markers: No specific delimiters are used to isolate learned content. 3. Capability inventory: The skill provides platform instructions and suggests tool installation. 4. Sanitization: No explicit sanitization of learned entries is mentioned. This is evaluated as a safe mechanism for maintaining user preferences across sessions within the local environment.
Audit Metadata