persona-ci-integration
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill facilitates communication with the Persona API using standard methods. Credentials are managed via environment variables (PERSONA_API_KEY), which is a secure practice for CI/CD environments. External communication is limited to the official withpersona.com domain.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests data from the external Persona API, creating a potential attack surface for indirect prompt injection if the API response contains malicious instructions designed to influence the agent. 1. Ingestion points: Data is retrieved from https://withpersona.com/api/v1/inquiries in SKILL.md. 2. Boundary markers: None identified in the provided script. 3. Capability inventory: The skill context includes tools like Read, Write, Edit, and GitHub CLI (gh). 4. Sanitization: No explicit sanitization or validation of the API response data is performed before printing.
Audit Metadata