prompt-optimizer
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as an advisory assistant, providing prompt analysis and recommendations without executing system commands, modifying files, or performing network operations.
- [SAFE]: File system access in Phase 0 is limited to a predefined set of standard project configuration files used strictly for identifying the technology stack and project conventions.
- [PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection as it processes untrusted user prompts during its analysis pipeline.
- Ingestion points: User-provided draft prompts processed by the analysis pipeline described in SKILL.md.
- Boundary markers: Absent; the instructions do not define specific delimiters or "ignore embedded instructions" warnings for the agent when processing the user's input.
- Capability inventory: The skill is limited to reading specific project files (Phase 0) and does not possess capabilities for file writing, system modification, or network communication.
- Sanitization: None; the skill does not implement content filtering or sanitization of the draft prompts before processing.
Audit Metadata