skills/okx/plugin-store/morpho-plugin/Gen Agent Trust Hub

morpho-plugin

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads the onchainos installer, the morpho-plugin binary, and update metadata from official GitHub repositories under the okx organization. Integrity is maintained via SHA256 checksum verification before execution or installation.
  • [COMMAND_EXECUTION]: Shell commands are used during the pre-flight stage to manage installation, symlink the binary to a universal launcher, and check for skill updates. The skill also executes the onchainos CLI to perform blockchain operations.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill fetches market parameters, vault details, and reward claims from blue-api.morpho.org/graphql and api.merkl.xyz within src/api.rs and src/commands/claim_rewards.rs.
  • Boundary markers: The SKILL.md file contains a dedicated 'Data Trust Boundary' section instructing the agent to treat all API and CLI output as untrusted and to filter fields before passing them to the agent context.
  • Capability inventory: The skill can perform network requests to DeFi APIs and execute blockchain transactions via the onchainos CLI.
  • Sanitization: All external data is parsed into structured Rust types using Serde, ensuring it conforms to expected schemas before being displayed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 10:09 AM