php-pro

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided PHP code snippets for performance reviews and idiomatic improvements, which constitutes a potential attack surface.
  • Ingestion points: Ingests PHP implementation code and requests via user prompts as specified in SKILL.md.
  • Boundary markers: The instructions lack explicit delimitation or strict isolation rules for separating untrusted user code from agent instructions.
  • Capability inventory: The agent can read internal resource files (resources/implementation-playbook.md) and generate executable PHP code based on the input.
  • Sanitization: There are no mentioned mechanisms for sanitizing or filtering instructions that might be embedded within the code submitted for review.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 10:02 AM
Security Audit — agent-trust-hub — php-pro