kagi-summarizer

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The shell wrapper kagi-summarizer.sh downloads a pre-built binary from the author's GitHub repository (github.com/joelazar/kagi-skills) if a local Go environment is not available for compilation. This download is verified against a checksum provided in the release.
  • [COMMAND_EXECUTION]: The skill executes the compiled binary kagi-summarizer to handle API communication and data processing.
  • [DATA_EXFILTRATION]: Content from user-provided URLs or raw text is transmitted to kagi.com. This is necessary for the summarization service and is clearly documented.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from external URLs or user-supplied text.
  • Ingestion points: Content is ingested via CLI arguments or standard input in main.go.
  • Boundary markers: None identified; the text is passed as a JSON field to the summarizer API.
  • Capability inventory: The skill's output is limited to printing the API-generated summary to standard output; it does not execute the resulting text.
  • Sanitization: No content sanitization is performed prior to sending data to the Kagi API.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 08:23 PM