get-url
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves content from external URLs and provides it to the agent. This creates a surface where a malicious website could include instructions aimed at overriding the agent's behavior or exfiltrating data.
- Ingestion points: Web content retrieved via the
npx playbooks getcommand inSKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the fetched content as untrusted data.
- Capability inventory: The skill can fetch arbitrary URLs and write the output to the local file system.
- Sanitization: There is no evidence of sanitization or filtering of the fetched content before it is processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill relies on
npx playbooks, which downloads and executes a package from the NPM registry at runtime. The dependency is not pinned to a specific version. - [COMMAND_EXECUTION]: The skill executes shell commands using
npxto perform web scraping and file writing tasks based on user-supplied URLs and paths.
Audit Metadata