meme-rush
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes subcommands via a local Node.js script (
scripts/cli.mjs) to interact with blockchain market data feeds. This is the primary intended function of the skill. - [EXTERNAL_DOWNLOADS]: The skill connects to official vendor domains to fetch live cryptocurrency lifecycle data and market narratives.
- Target Domains:
web3.binance.com(API) andbin.bnbstatic.com(CDN for icons). - Assessment: These are legitimate resources owned by the author/vendor (Binance).
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content, specifically token symbols, names, and AI-generated summaries (
narrativeText,aiSummary) from the Binance API. Because this data is interpreted by the agent, it represents an injection surface. - Ingestion points: API responses returned via
meme-rushandtopic-rushsubcommands documented inSKILL.mdandscripts/cli.mjs. - Boundary markers: Absent; the skill does not explicitly instruct the agent to use XML tags or other delimiters to isolate the potential instruction-carrying data from the API.
- Capability inventory: Local script execution (
node) and file read access for icon rendering. - Sanitization: Absent; the agent is expected to process the raw string data returned by the CLI for display to the user.
Audit Metadata