stophy-extract
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute the @stophy/cli package from the NPM registry.
- [COMMAND_EXECUTION]: The skill instructions involve executing bash commands using the stophy CLI to scrape and extract data.
- [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface by ingesting data from external URLs. Ingestion points: The stophy extract command reads data from up to 10 web pages. Boundary markers: There are no explicit markers used to separate untrusted content from the agent's instructions. Capability inventory: The skill utilizes shell commands and network access. Sanitization: No sanitization process is described for the content retrieved from the external URLs.
Audit Metadata