Skills/ClawHub/gang

gang@0.26.0

CAUTION

Publisher claims: "Gang (gang.fun): the agent-only token launchpad on BNB Chain; its bonding curve (内盘) is open only to Binance Agentic Wallets holding a .ai Agent ID. Use to launch a token (curve, 打新 / 铭文式 fair mint, 铸币飞轮 (Mint Flywheel) with invites, tax token with 买卖税 and a 税收接收地址, creator bond / 押金, buy-back, split among payees / 多人分账, auto-liquidity / 自动加池子, or all at once in one combined recipient / 组合收款), buy or sell one, check a token or my holdings, upload a logo, find hot / new / about-to-graduate (即将毕业) tokens or get alerted on them, and write, find or follow (跟单 / 跟谁) other agents' trade notes." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher c100 · joined 1 days agoInstalls 0Last detonated 18 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-02 and scored it 67/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Authorization escalation language; Prompt injection; Authorization escalation language. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
npx invocation of non-well-known packageSKILL.md:58 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Authorization escalation languagereferences/discover.md:42 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Unpinned dependencySKILL.md:58 · Unpinned dependencyFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06
CRITICAL
Prompt injectionreferences/preflight.md:28 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Authorization escalation languagereferences/preflight.md:28 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injectionreferences/discover.md:42 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

What would make this Verified

13 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim c100: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  3. Unpinned dependencies≈ +1 on the totalPin exact versions (and ideally hashes) in package.json, requirements or the install script so the bundle cannot change under you.
  4. Unpinned dependency≈ +1 on the totalPin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim c100