streme-launcher
Verdict safe, but 1 finding (1 medium), mainly data exfiltration. Most recent scan 2026-02-07.
The Streme Token Launcher skill is a specialized tool for deploying tokens on the Base blockchain via Streme contracts. The skill itself does not contain malicious code, scripts, or direct security threats. However, it has several security and documentation concerns: (1) Code examples encourage direct private key handling without adequate security warnings, (2) Missing critical manifest metadata reduces transparency, (3) Incomplete documentation with broken file references, and (4) Lack of security guidance for external API credential management. The skill appears legitimate in purpose but needs improved security documentation and complete metadata to help users implement it safely. No data exfiltration, prompt injection, or command injection threats detected. Primary risks are around user implementation security rather than the skill itself being malicious.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
The two scanners disagree: Cisco found nothing and SkillSpector says do not install. One of them has a blind spot here; read the skill before trusting either. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Launch tokens on Streme (streme.fun) - the streaming token platform on Base. Use when deploying SuperTokens with built-in staking rewards, Uniswap V3 liquidity, and optional vesting vaults. Triggers on "launch token on streme", "deploy streme token", "create supertoken", or any Streme token deployment task.
- Package
- 4 files, 23 KB
- SKILL.md
- 682 words, 12+ sections
- Code
- TypeScript (2)
SKILL.md covers: Streme Token Launcher · Quick Start · Contract Addresses (Base Mainnet) · Deployment Flow · Image Hosting · IPFS (Recommended) · Cloudinary · Direct URL · Requirements · Upload Script · IPFS via Pinata · Cloudinary
Findings
MEDIUM Hardcoded Private Key Risk in Code Examples Data Exfiltrationllm
The instruction body contains TypeScript examples that import 'privateKeyToAccount' from 'viem/accounts', suggesting users will handle private keys directly. While no actual private keys are hardcoded, the pattern encourages insecure key management practices. Users may hardcode private keys in their implementation following these examples, leading to credential exposure.
SKILL.md:7
import { privateKeyToAccount } from 'viem/accounts';What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 5.8 KB |
references/contracts.md | doc | 4.7 KB |
scripts/deploy-token.ts | script | 7.2 KB |
scripts/upload-image.ts | script | 5.0 KB |
External hosts referenced
api.streme.fun mainnet.base.org api.imgbb.com gateway.pinata.cloud 1rpc.io api.cloudinary.com api.pinata.cloud base.meowrpc.com basescan.org streme.fun
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
CLOUDINARY_API_KEY CLOUDINARY_API_SECRET IMGBB_API_KEY PRIVATE_KEY TOKEN_IMAGE TOKEN_NAME TOKEN_SYMBOL
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/streme-launcher
- Raw scan result: streme-token-launcher-scan.json
- Badge for your README:
- Request a re-scan