hasdata-cli
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the hasdata CLI tool by downloading an installation script directly from the author's official GitHub repository (https://raw.githubusercontent.com/HasData/hasdata-cli/main/install.sh).
- [REMOTE_CODE_EXECUTION]: The recommended installation method involves piping a remote shell script directly into the shell (curl -sSL ... | sh). This is the intended installation mechanism for the vendor's own tool and originates from a verified source matching the skill author's context.
- [COMMAND_EXECUTION]: The skill's primary functionality relies on executing the hasdata CLI tool and various shell utilities like jq and xargs to process and filter web data.
- [DATA_EXFILTRATION]: The skill reads the user's API key from the configuration file ~/.hasdata/config.yaml and sends web scraping/search requests to the vendor's API endpoint (api.hasdata.com) to fulfill user requests.
- [PROMPT_INJECTION]: The skill acts as an ingestion point for untrusted external web content (search results, scraped HTML, YouTube transcripts). Ingestion points: Web data from various hasdata subcommands. Boundary markers: Absent. Capability inventory: Subprocess calls (CLI execution), file writes (via -o flag), and network operations (API calls). Sanitization: Absent. This represents an indirect prompt injection surface.
Audit Metadata