persona-deploy-integration

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from an external API, creating a potential surface for indirect prompt injection.
  • Ingestion points: The Python implementation in SKILL.md fetches inquiry records from https://withpersona.com/api/v1/inquiries and prints IDs and attributes to the console.
  • Boundary markers: None. The skill does not use delimiters or instructions to ignore potential commands embedded within the inquiry data.
  • Capability inventory: The skill has access to sensitive tools including Bash(gcloud:*), Read, Write, and Edit, which could be targeted by instructions hidden in the API response.
  • Sanitization: None detected. The script directly prints inquiry IDs and status attributes without filtering or validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 03:36 PM
Security Audit — agent-trust-hub — persona-deploy-integration