shipmytoken

Fail

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • CREDENTIALS_UNSAFE (HIGH): The skill documentation (CHANGELOG.md) explicitly states it performs 'Secure wallet creation and backup' with data stored in ~/.shipmytoken/. Managing and storing raw private keys on the filesystem is a high-risk activity for AI agents.
  • COMMAND_EXECUTION (HIGH): The skill configures system-level persistence using cron for daily recaps and executes external CLI tools like solana-keygen for vanity address generation.
  • PROMPT_INJECTION (LOW): The skill ingests untrusted data such as token names, symbols, and metadata. This presents a surface for indirect prompt injection if the agent interpolates this data into its own reasoning or prompts without sanitization.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 19, 2026, 12:23 AM