summarize
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the 'summarize' binary from the 'steipete/tap/summarize' Homebrew tap during the setup process.
- [COMMAND_EXECUTION]: The skill executes the 'summarize' CLI tool to perform content extraction and summarization tasks based on user-provided input.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the processing of untrusted external content.
- Ingestion points: Content is ingested from user-provided URLs, YouTube video transcripts, and local file paths.
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the command construction provided in the skill documentation.
- Capability inventory: The skill executes shell commands ('summarize') and has network access to fetch web data and YouTube transcriptions.
- Sanitization: No input sanitization or content filtering is defined within the skill's instructions.
Audit Metadata