Skill flagged — suspicious patterns detected

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

Arming Thought

v1.0.0

触发:在每次新的顶层对话开始时自动调用,用于先建立“实事求是”的总原则,并判断后续应调用哪一种 skill;如果你是被派遣执行单一具体任务的子 agent,则跳过此 skill。 English: Trigger at the start of every new top-level conversation t...

0· 72·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Name/description match the instructions: it is a top-level 'thought-arming' dispatcher that sets methodology and decides which downstream skill to call. No binaries, env vars, or installs are requested, which is proportionate. However, the content explicitly elevates a specific political/ideological framework (Mao Zedong thought) as the guiding principle — that is a design choice but not strictly necessary for a neutral 'dispatcher' and may be unexpected for many users.
!
Instruction Scope
The SKILL.md instructs the agent to adopt an ideological stance and to enforce a strict calling policy: if there's even a 1% chance a thought-weapon applies, the agent 'must' call the corresponding skill. It also states that '毛泽东思想 skills' override default system behavior. These are broad, prescriptive runtime behaviors that go beyond simply deciding which skill to call and could cause frequent, possibly unnecessary autonomous calls to other skills, increasing attack surface and unexpected side effects.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest installation risk. Nothing is downloaded or written to disk by the skill itself.
Credentials
No environment variables, credentials, or config paths are requested. The skill does not ask for secrets or system access by itself.
!
Persistence & Privilege
always:false (good), and the skill is not force-installed. However, the instructions try to change instruction priority ordering (placing these 'Mao thought' skills above default system prompts) and mandate aggressive autonomous calls. Combined with normal autonomous invocation, this could grant the skill outsized runtime influence over agent behavior even without explicit platform-level privileges.
What to consider before installing
This skill is a methodology dispatcher that embeds Mao Zedong–based guidance and requires the agent to aggressively invoke other skills (if any apply at all, even at 1% likelihood). Before installing, consider: - Do you want an ideological framework to shape every top-level conversation? The content explicitly instructs the agent to adopt specific political doctrine and to treat those skills as high-priority. - Which downstream skills (e.g., contradiction-analysis, investigation-first, mass-line, etc.) will be called, and what permissions/credentials do those skills require? The dispatcher itself asks for nothing, but calling other skills can trigger them to access data or credentials. - The 1% rule and 'must call' language can cause many autonomous invocations and unexpected behavior. If you proceed, restrict autonomous invocation or review/limit the dispatcher rules (remove the 1% mandatory-call policy and the instruction to override system-level prompts). - Because the source/homepage is unknown, exercise extra caution. If you cannot verify author intent or inspect downstream skills, do not enable this skill for agents that handle sensitive data or run unattended. If you want a safer alternative: request a neutral dispatcher that (a) documents exact conditions for calling each downstream skill, (b) defers to system prompts unless the user explicitly consents, and (c) removes ideological indoctrination and the '1% must call' mandate.

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

latestvk977zrwyj1yj73nrfdm0hvvmg983sejh

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments