Caveat verdict
tianji-fengshui
The skill explicitly discloses reading ~/.openclaw/openclaw.json (which may contain more keys than needed) and sending image data to Volcengine and DeepSeek endpoints; reading a shared config file with potentially excess keys and transmitting content to third-party cloud providers is a genuine risk even though disclosed.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (5)
Possible hardcoded credential
SKILL.md · frontmatter · API_KEY:', os.getenv(
Pipe to python — executes piped content as Python code
skills/baidu-search/references/apikey-fetch.md · code · | python
Accesses OpenClaw config/secrets directly
SKILL.md · frontmatter · ~/.openclaw/openclaw.json
Python os.getenv — reads environment variable
SKILL.md · frontmatter · os.getenv(
References agent memory files
knowledge/fengshui_bazi_palm_books.md · prose · downgraded · MEMORY.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.