prompt-enhance

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a prompt engineering tool designed to optimize LLM instructions through compression and attention anchoring techniques.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external files and text provided via arguments ($ARGUMENTS). 1. Ingestion points: $ARGUMENTS in SKILL.md. 2. Boundary markers: Uses XML-like tags to wrap target data. 3. Capability inventory: Uses file reading and spawn_agent (standard tools). 4. Sanitization: Relies on Phase 0 classification to route data handling. This is a standard attack surface for this type of tool and does not indicate malicious intent.
  • [REMOTE_CODE_EXECUTION]: No remote script execution or external package installations were detected. The skill mentions subagent authorization for spawn_agent, which is a standard platform capability.
  • [DATA_EXFILTRATION]: No network operations or access to sensitive system files (like credentials or SSH keys) were found. The skill only accesses files within the designated project environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 10:11 AM