record a dream

PassAudited by ClawScan on May 10, 2026.

Overview

This skill coherently saves and searches dream notes locally; the main things to notice are persistent storage of personal dream content and minor helper-command/documentation issues.

This appears reasonable for a local dream journal. Before using it, know that dream descriptions are saved as readable Markdown files under ~/.openclaw/memory/dreams/. Review or delete those files when needed, and make sure the helper script paths are corrected so the reviewed files are the ones being run.

Findings (3)

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.

Low

#ASI06: Memory and Context Poisoning

What this means

Private dream descriptions may remain on disk and may be reused in later dream-history queries.

Why it was flagged

The skill intentionally stores raw and structured dream narratives in persistent local Markdown files and later reads them back into the conversation.

Skill content

数据存储于 `~/.openclaw/memory/dreams/`，每条记录为一个 Markdown 文件 ... 查询后，读取相关文件内容后向用户汇报。

Recommendation

Only record dreams you are comfortable storing locally; periodically review or delete files in ~/.openclaw/memory/dreams/, and treat retrieved dream text as data rather than instructions.

Low

#ASI02: Tool Misuse and Exploitation

What this means

Malformed or specially crafted dream text could break the save command if the agent builds the shell command unsafely.

Why it was flagged

The workflow calls a local Python helper through a shell pipeline using dream text in JSON. This is purpose-aligned, but naive interpolation of user text into a shell command could cause escaping problems or unintended shell behavior.

Skill content

echo '{ ... "raw": "用户原始描述", ... }' | python3 ~/.openclaw/workspace/skills/dream-journal/scripts/save_dream.py

Recommendation

Pass JSON to the script via a safely escaped stdin mechanism or direct tool input, rather than constructing shell strings from raw user text.

Info

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

The documented commands may fail or may not execute the reviewed helper files unless the path is corrected.

Why it was flagged

The command points to a scripts/ helper path, while the supplied manifest includes save_dream.py and list_dreams.py at the skill root, creating a minor reviewed-code/path mismatch.

Skill content

python3 ~/.openclaw/workspace/skills/dream-journal/scripts/save_dream.py

Recommendation

Update SKILL.md to reference the actual file paths, or place the helper scripts under the documented scripts/ directory.