acc-check-fallback-strategy

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOWNO_CODEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes untrusted PHP source code, creating a potential ingestion surface for malicious instructions.
  • Ingestion points: Processes PHP files identified via grep patterns in infrastructure and application directories.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded instructions within the analyzed code.
  • Capability inventory: The skill's capabilities are limited to generating markdown reports and descriptions; it lacks file-write, network access, or command execution capabilities.
  • Sanitization: No sanitization or filtering of the analyzed content is defined before its inclusion in the output.
  • NO_CODE (SAFE): The skill consists entirely of markdown instructions, grep search patterns, and code examples for static analysis, with no embedded executable scripts or automation routines.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 09:36 AM