phoenix-json-api

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for ingesting and processing external data via API request parameters, creating a potential surface for indirect prompt injection.
  • Ingestion points: The params variable in PostController.index/2 and PostController.create/2 functions within SKILL.md serves as the entry point for untrusted external data.
  • Boundary markers: The instructions do not specify explicit boundary markers or delimiters for the ingested data within the prompts, relying on standard Phoenix parameter parsing.
  • Capability inventory: The controller patterns involve database interactions via context modules (Blog.list_posts, Blog.create_post) and rendering JSON responses to the client.
  • Sanitization: The skill implements sanitization best practices, including explicit field selection in the post_json/1 function to prevent sensitive data leakage and a parse_int utility to validate and bound pagination parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 12:25 AM
Security Audit — agent-trust-hub — phoenix-json-api