hasdata-cli
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides an installation command that downloads a script from the author's GitHub repository: https://raw.githubusercontent.com/HasData/hasdata-cli/main/install.sh. As this is an official vendor resource hosted on a well-known service, it is a standard deployment pattern for this tool.
- [REMOTE_CODE_EXECUTION]: The installation process pipes the downloaded script directly into a shell (sh) for execution. While this facilitates automated setup, it bypasses the manual review of the script content before it runs.
- [COMMAND_EXECUTION]: The instructions extensively use local shell command execution, invoking the hasdata CLI and utility tools like jq, curl, and xargs to process and pipe data.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a bridge for the agent to ingest content from external web pages, YouTube transcripts, and search engine results, creating an ingestion surface for untrusted data.
- Ingestion points: Web data from Google, Bing, Amazon, YouTube, and arbitrary URLs is fetched and processed via hasdata CLI subcommands (SKILL.md, references/*.md).
- Boundary markers: The instructions do not explicitly mandate the use of delimiters or warnings for the agent to ignore instructions embedded within retrieved data.
- Capability inventory: The agent has the ability to execute shell commands, perform network requests via the CLI, and write output to the file system (SKILL.md).
- Sanitization: The instructions do not describe any sanitization or escaping of the external content before it is interpolated into the agent's context.
Audit Metadata