summarize

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill defines an installation step to fetch and install the summarize command-line tool via a Homebrew tap (steipete/tap/summarize). This is a standard software distribution method for CLI utilities.
  • [COMMAND_EXECUTION]: The skill operates by executing the summarize command in a shell environment to process various targets, including website URLs, local PDF files, and YouTube video links.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from the web and local file system, creating an attack surface where malicious instructions embedded in that data could potentially influence the agent's behavior.
  • Ingestion points: Website URLs, local file paths, and YouTube links are passed directly to the summarize binary for processing.
  • Boundary markers: The skill does not provide specific delimiters or instructions to the agent to distinguish between summarized content and its own operating instructions.
  • Capability inventory: The skill possesses the ability to execute shell commands using the summarize tool.
  • Sanitization: There is no explicit sanitization or filtering of the content retrieved from external sources within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 07:40 AM