opensea
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes shell commands via
npx,curl, and local scripts to perform marketplace operations and trade fulfillment. - [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: Downloads and runs the official
@opensea/clipackage from the npm registry usingnpxat runtime. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the OpenSea marketplace which could contain malicious instructions.
- Ingestion points: Marketplace data retrieved via
opensea search,opensea listings, andopensea events(SKILL.md, references/marketplace.md). - Boundary markers: Absent; instructions do not provide delimiters or warnings to distinguish external data from agent commands.
- Capability inventory: Shell command execution and network requests via
curl(SKILL.md, references/marketplace.md). - Sanitization: No content sanitization or instruction filtering is implemented for data fetched from the marketplace.
Audit Metadata