skills/smallnest/goclaw/summarize/Gen Agent Trust Hub

summarize

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires installing the 'summarize' CLI utility from a third-party Homebrew tap ('steipete/tap/summarize') which is not on the trusted vendor list.
  • [COMMAND_EXECUTION]: The skill executes the 'summarize' binary using user-provided parameters such as URLs and local file paths.
  • [PROMPT_INJECTION]: The skill processes untrusted data from URLs, YouTube transcripts, and local files which creates an indirect prompt injection surface. Ingestion points: URLs, YouTube links, local files. Boundary markers: None. Capability inventory: execution of the 'summarize' binary. Sanitization: None mentioned.
  • [CREDENTIALS_UNSAFE]: The skill uses environment variables (e.g., 'OPENAI_API_KEY', 'GEMINI_API_KEY') and a configuration file ('~/.summarize/config.json') for API key management.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 02:45 PM