grimoire-morpho-blue

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use npx -y @grimoirelabs/cli, which downloads and executes the Grimoire CLI from the NPM registry. It also references the @grimoirelabs/venues package. These are verified as vendor resources associated with the skill's Grimoire ecosystem.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands through grimoire, npx, and bun to perform metadata queries and snapshot operations.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from the Morpho Blue protocol, creating an indirect prompt injection surface.
  • Ingestion points: Output from the grimoire venue morpho-blue CLI commands (SKILL.md).
  • Boundary markers: Absent; there are no specific instructions for the agent to use delimiters or ignore embedded instructions when parsing fetched metadata.
  • Capability inventory: The agent has the capability to execute shell commands and interact with the local filesystem as part of the CLI workflow.
  • Sanitization: The instructions do not define any validation, filtering, or escaping protocols for data retrieved from external protocol sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 02:51 PM