token-scam-analysis
Warn
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to dynamically generate a JavaScript file (analyze.mjs) and execute it using the execute_cli tool to perform complex blockchain data retrieval.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests data from untrusted external sources, including blockchain contract metadata, social media sentiment, and search engine results. (1) Ingestion points: Data enters through tools such as read_contract, search_tool, get_social_sentiment_for_ticker, and browse_url. (2) Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the ingested data. (3) Capability inventory: The agent has the ability to execute shell commands via execute_cli and write analysis reports to the local filesystem. (4) Sanitization: There is no mention of sanitizing or escaping content retrieved from external APIs or websites before it is processed or included in reports.
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the viem package at runtime to facilitate blockchain interactions.
Audit Metadata