acc-check-class-length

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • [SAFE] (SAFE): The content consists entirely of markdown-based documentation and PHP code examples used for pattern matching and architectural analysis.
  • [Indirect Prompt Injection] (LOW): While the skill is intended to process untrusted external data (PHP source code), it does not define any tools or scripts with write/execution capabilities. The risk is limited to affecting the agent's internal reasoning or analysis output when viewing potentially malicious code snippets.
  • Ingestion points: PHP code files provided to the agent for review.
  • Boundary markers: None explicitly defined in the instruction body.
  • Capability inventory: None; the skill provides logic for the LLM's reasoning rather than defining tool-based capabilities like file system writes or network requests.
  • Sanitization: None required for the instructional content provided.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 09:28 AM