Prompt Optimizer
ReviewAudited by ClawScan on May 10, 2026.
Overview
Prompt-injection indicators were detected in the submitted artifacts (system-prompt-override); human review is required before treating this skill as clean.
This appears safe for normal prompt-writing help, but remember that saved prompts and history are written locally under ~/.openclaw/prompt-optimizer/. Avoid saving sensitive information there unless you are comfortable retaining it on disk. ClawScan detected prompt-injection indicators (system-prompt-override), so this skill requires review even though the model response was benign.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The skill may create and update local files for its own prompt library and statistics.
The skill requests file read/write capability, but the documented scope is a local skill-specific directory for settings, history, and saved prompts.
requires":{"tools":["read","write"]} ... Only reads/writes files under `~/.openclaw/prompt-optimizer/`Verify that any file writes remain under ~/.openclaw/prompt-optimizer/ and do not save sensitive prompts unless intended.
Prompt drafts, examples, or sensitive text included in prompts may remain on disk after the conversation.
The skill stores saved prompts and optimization history, which may include user-provided prompt text and could be read or reused later.
`library.json` — saved prompt library; `history.json` — optimization history
Do not save secrets or private data in prompts, and periodically review or delete ~/.openclaw/prompt-optimizer/ if retention is not desired.