opensea
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto dynamically fetch the@opensea/clipackage from the npm registry during runtime.\n- [REMOTE_CODE_EXECUTION]: The execution of the@opensea/clipackage vianpxconstitutes running code from a remote source, which is standard for this marketplace tool but represents a dependency on the package's integrity.\n- [COMMAND_EXECUTION]: The skill relies on local shell scripts likeopensea-fulfill-listing.shandopensea-post.shto interact with the OpenSea API and process blockchain transaction data usingcurlandjq.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the external OpenSea marketplace API (such as collection listings and events), creating a surface for indirect prompt injection.\n - Ingestion points: External data from the OpenSea REST API and real-time event streams.\n
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between marketplace data and operational commands.\n
- Capability inventory: The skill can execute network requests (
curl), run external packages (npx), and generate transaction calldata for wallet execution.\n - Sanitization: The documentation does not specify any sanitization or validation logic for the ingested external data beyond basic formatting.
Audit Metadata