skills/swiftyjunnos/skills/unslop/Gen Agent Trust Hub

unslop

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions for text refinement. No security issues were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite user-provided text. While this is a surface for indirect prompt injection, the skill lacks any dangerous capabilities (like network access or command execution) that could be exploited through such an injection.
  • Ingestion points: Processes text provided in the agent's context during writing/editing tasks.
  • Boundary markers: None explicitly defined in the instructions, but the output is intended to be rewritten text.
  • Capability inventory: No subprocess calls, file writes, or network operations are present in the skill.
  • Sanitization: The skill focuses on linguistic transformation rather than data sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 04:27 AM
Security Audit — agent-trust-hub — unslop