acc-find-type-issues
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- Prompt Injection (SAFE): No override markers, bypass instructions, or system prompt extraction patterns were detected.
- Data Exposure & Exfiltration (SAFE): The skill does not access sensitive files like credentials or SSH keys and has no network communication logic.
- Remote Code Execution (SAFE): There are no patterns involving external script downloads or execution of remote content.
- Indirect Prompt Injection (LOW): The skill ingests untrusted PHP code via grep patterns (Ingestion: local PHP files; Boundary markers: None; Capabilities: Local grep only; Sanitization: None). While an attack surface exists, the skill lacks the necessary capabilities (write, execute, or network) to facilitate an exploit.
Audit Metadata