php-cmd-audit

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill performs static analysis on external PHP source code, which serves as a potential vector for indirect prompt injection.
  • Ingestion points: Untrusted source code files from the PHP project being audited.
  • Boundary markers: The instructions lack specific delimiters or isolation rules for the code content, allowing potential instructions hidden in comments or strings to influence the agent's reasoning.
  • Capability inventory: The agent is authorized to read project files, write detailed audit reports (including PoCs) to the local file system, and invoke external analysis capabilities such as php-route-tracer.
  • Sanitization: No explicit sanitization, filtering, or validation is performed on the content of the files before the agent processes and interprets them.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 12:59 AM
Security Audit — agent-trust-hub — php-cmd-audit