grimoire-morpho-blue

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface by consuming external protocol metadata to influence agent-authored financial transactions.
  • Ingestion points: Market metadata and vault snapshots fetched via the vaults-snapshot command in SKILL.md.
  • Boundary markers: No instructions or delimiters are provided to the agent to treat the fetched metadata as untrusted data when interpolating it into parameters.
  • Capability inventory: The skill provides templates for high-value financial actions including morpho_blue.lend, morpho_blue.borrow, morpho_blue.supply_collateral, and morpho_blue.vault_deposit.
  • Sanitization: There is no evidence of validation or sanitization of the externally sourced market data before it is used to construct transaction sequences.
  • [COMMAND_EXECUTION]: The skill relies on the execution of shell commands through the grimoire CLI to retrieve protocol metadata and check liquidity.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download and execution of external code from a public registry. It recommends the use of npx -y @grimoirelabs/cli, which fetches the package from the NPM registry at runtime. While the registry is a well-known service, the package originates from an unverified third-party account.
  • [REMOTE_CODE_EXECUTION]: The recommendation to execute unverified packages via npx from a public registry constitutes a remote code execution pattern.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 11:09 PM