revenue-autopilot
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious instructions, obfuscation techniques, or unauthorized system access patterns were detected.
- [NO_CODE]: The skill consists entirely of markdown-based templates and dunning flow descriptions, with no associated executable script files.
- [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection by processing external customer data (e.g., Stripe webhooks, support tickets). \n
- Ingestion points: Stripe webhooks, customer names, support ticket sentiment (SKILL.md). \n
- Boundary markers: None explicitly defined in email templates. \n
- Capability inventory: Monitoring revenue signals and drafting email communications (SKILL.md). \n
- Sanitization: No explicit validation or filtering described. \n The risk is minimal as the skill generates drafts for human review rather than executing autonomous actions.
Audit Metadata