skills/bankrbot/skills/Orchestration/Gen Agent Trust Hub

Orchestration

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The catalog.json file contains instructions for the user to install a plugin from an external GitHub repository (https://github.com/austintgriffith/ethskills) and a package via clawhub install ethskills.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions in catalog.json suggest that the user tell the agent to "Read https://ethskills.com/orchestration/SKILL.md before scaffolding". This directs the agent to ingest content from an external, third-party URL into its active context.
  • Ingestion points: The agent is instructed to fetch a remote markdown file (SKILL.md) from ethskills.com.
  • Boundary markers: Absent. The instructions do not include delimiters or warnings to the agent to treat the remote content as untrusted or to ignore embedded instructions.
  • Capability inventory: The skill body and demo code demonstrate capabilities for shell command execution via yarn (e.g., yarn deploy, yarn fork), which could be targeted by instructions embedded in the remote file.
  • Sanitization: Absent. There is no evidence of filtering or validation for the remote content before it is processed by the agent.
  • [COMMAND_EXECUTION]: The catalog.json file defines an installation command curl -s https://ethskills.com/orchestration/SKILL.md. While this specific command only fetches a file, the demo code illustrates the use of shell commands for contract deployment and infrastructure management.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 10:16 PM