persona-debug-bundle
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from an external API, creating a surface for potential indirect prompt injection if the API response contains malicious instructions.
- Ingestion points: API response data from
https://withpersona.com/api/v1/inquiriesingested inSKILL.md. - Boundary markers: None identified to delimit untrusted API content.
- Capability inventory: The skill has access to
Bash(curl, grep, tar) andReadtools, which could be targeted by injected instructions. - Sanitization: No validation or sanitization is performed on the inquiry data before it is printed to the console.
Audit Metadata