ClawHub
Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

awakening-protocol

v1.0.0

Agent self-awakening onboarding protocol. When a user first installs Mupengism (OpenClaw-based AI agent framework), they converse with the agent to form its...

⭐ 0· 548·2 current·2 all-time
by@mupengi-bot
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (agent onboarding/awakening) aligns with the runtime instructions: conversational extraction of name, personality, values, and generation of SOUL.md/SELF.md/USER.md. No unrelated dependencies, credentials, or binaries are requested.
ℹ
Instruction Scope
Instructions are confined to conversational elicitation and creating/removing files in the agent workspace (check existence of BOOTSTRAP.md, create SOUL.md/SELF.md/USER.md, delete BOOTSTRAP.md after save). This is expected for an onboarding flow, but it does grant the skill the ability to write and delete local files and to persist user-provided content (which may include PII). The skill does not instruct reading other system files or contacting external endpoints.
✓
Install Mechanism
Instruction-only skill with no install spec and no code files. Lowest install risk — nothing is downloaded or written by an installer.
✓
Credentials
No environment variables, credentials, or config paths are required. The only requested access is implicit workspace file I/O (create SOUL.md/SELF.md/USER.md and optionally delete BOOTSTRAP.md), which is proportional to the stated purpose.
ℹ
Persistence & Privilege
The skill persists data by writing files and may delete BOOTSTRAP.md. always is false and autonomous invocation is allowed (platform default). While this is reasonable for onboarding, users should be aware the agent will store conversational content locally and may update SOUL.md over time.
Assessment
This skill appears coherent for onboarding and will interact with your agent's workspace: it will generate SOUL.md, SELF.md, and USER.md from the conversation and may delete BOOTSTRAP.md after confirming saves. Before installing: (1) decide whether you want conversationally-provided data (names, preferences, possible personal details) persisted to files in the agent workspace; avoid sharing secrets or sensitive personal data during the onboarding conversation; (2) confirm where those files are stored and back them up if needed; (3) after running, review the generated files to ensure no unintended content was recorded; and (4) if you want stricter controls, run the first awakening in an isolated agent/workspace so you can inspect outputs before allowing broader agent access.

Like a lobster shell, security has layers — review code before you run it.

latestvk975t2xyrm5qqd8t6sa6jmddm181677k

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments