prompt-optimizer

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown instructions for the AI agent to follow. There are no executable scripts, binaries, or configuration files that could carry out malicious actions.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted user input (rough drafts or task descriptions) and transform them into structured prompts.
  • Ingestion points: The skill ingests user-provided text pasted into the chat interface (SKILL.md).
  • Boundary markers: The instructions recommend using XML tags such as <instructions>, <context>, and <input> to structure the generated output, which helps delineate sections.
  • Capability inventory: The skill has no associated code capabilities, network tools, or filesystem access.
  • Sanitization: There is no explicit sanitization of user input, but the lack of executable capabilities makes this surface low risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:57 AM
Security Audit — agent-trust-hub — prompt-optimizer