summarize

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requests the installation of a binary from a third-party Homebrew tap (steipete/tap/summarize) which is not among the platform's trusted vendor repositories.
  • [COMMAND_EXECUTION]: The skill uses the 'summarize' CLI tool to process data, executing shell commands with arguments derived from user input such as URLs and file paths.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing external data without explicit isolation.
  • Ingestion points: Content from URLs, YouTube transcripts, and local files (SKILL.md).
  • Boundary markers: Absent; the skill does not specify delimiters or instructions to the model to ignore potential commands embedded in the summarized text.
  • Capability inventory: Shell execution of the 'summarize' command with access to local files and network (SKILL.md).
  • Sanitization: Absent; the tool does not describe any validation or filtering of the input content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 03:25 PM
Security Audit — agent-trust-hub — summarize