prompt-enhancer

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill's core functionality creates a surface for indirect prompt injection by taking arbitrary user input and instructing the agent to execute a transformed version of it.
  • Ingestion points: Raw user intent is ingested via the 'p:' or 'prompt:' prefix defined in SKILL.md.
  • Boundary markers: The instructions do not specify any delimiters or safety guidelines for the agent to use when handling the user-provided content.
  • Capability inventory: The agent is explicitly told to 'execute that enhanced prompt,' allowing untrusted input to directly influence agent behavior.
  • Sanitization: No validation or filtering is applied to the input to prevent malicious instructions from being incorporated into the enhanced prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 10:49 AM
Security Audit — agent-trust-hub — prompt-enhancer