moneybird
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto download and execute the@useclawlink/clipackage from the NPM registry. This is a vendor-owned resource corresponding to the skill author 'clawlink-hq' and is necessary for the skill's primary function. - [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using the ClawLink CLI to perform accounting actions, such as
npx @useclawlink/cli actions moneybird. These commands are standard for the skill's documented purpose. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided natural language strings by passing them to the
actionscommand of the CLI tool. This creates a surface where external or user-supplied instructions could influence the tool's behavior. - Ingestion points: User instructions are passed to the
<what you want to do>argument in the CLI commands documented inSKILL.md. - Boundary markers: No specific delimiters or boundary markers are defined for the user input strings.
- Capability inventory: The skill possesses the capability to execute shell commands (
npx), perform network operations (via the CLI), and access the local file system (~/.clawlink/credentials.json). - Sanitization: The skill relies on the external CLI tool and the agent's internal guardrails, as no explicit sanitization logic is provided in the skill markdown.
Audit Metadata