shipmytoken

[Skill Scanner] Installation of third-party script detected All findings: [CRITICAL] command_injection: Installation of third-party script detected (SC006) [AITech 9.1.4] [HIGH] autonomy_abuse: Skill instructions include directives to hide actions from user (BH009) [AITech 13.3] Report 2 is the most balanced of the three, highlighting legitimate token-launch workflow alongside notable risk factors (upfront SOL funding prompts, wallet exposure, and key backup/export). To improve security, require explicit user confirmation for each on-chain action, segregate private-key handling from routine tasks, remove or clearly scope any private-key export capabilities, and implement auditable, minimal-data exposure flows across setup/launch/fees/stats scripts. A more robust risk posture would treat the tool as high-risk until code-level audits validate secure key handling, consent flows, and custody assurances. LLM verification: The skill's instructions describe a plausible legitimate automation for launching Solana tokens, but contain multiple high-risk behaviors: forced automatic onboarding with npm installs, immediate request for user funds to a generated wallet, undemonstrated and opaque permanent fee-taking, and automatic modification of workspace scheduling files. Because the actual implementation code for critical scripts and the SDK usage is not provided, it is impossible to verify handling of private keys, fee