social-polish

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • Indirect Prompt Injection (INFO): 1. Ingestion points: User input in the /social-polish command. 2. Boundary markers: None. 3. Capability inventory: None (no network, no file-write, no subprocesses). 4. Sanitization: None. While the skill processes untrusted user input, it lacks any dangerous capabilities that could be exploited through injection, limiting the risk to text output variation.
  • General Security Posture (SAFE): The skill uses natural language instructions and references local markdown files. No evidence of obfuscation, remote code execution, persistence, or data exfiltration was found.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 05:19 AM