decodo-web-scraping
Fail
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill includes an installation command that fetches a shell script from the vendor's GitHub Pages site and pipes it directly to a shell:
curl -fsSL https://decodo.github.io/cli/install.sh | sh. - [EXTERNAL_DOWNLOADS]: The skill references and installs Node.js packages from the official NPM registry (
@decodo/cli,@decodo/mcp-server) and interacts with vendor-hosted API endpoints (mcp.decodo.com,scraper-api.decodo.com). - [COMMAND_EXECUTION]: The instructions involve executing the
decodoCLI to perform web scraping and data extraction, which includes the ability to write results to local files using the-oor--outputflags. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its core functionality.
- Ingestion points: Untrusted data from external websites is brought into the agent's context via the
decodo scrapeanddecodo searchcommands. - Boundary markers: The instructions do not define delimiters or specific system instructions to isolate the retrieved web content from the agent's internal logic.
- Capability inventory: The skill provides the agent with the ability to execute CLI commands and write files to the disk.
- Sanitization: There is no provided mechanism for sanitizing or escaping the scraped web content before it is processed by the agent.
Recommendations
- HIGH: Downloads and executes remote code from: https://decodo.github.io/cli/install.sh - DO NOT USE without thorough review
Audit Metadata