summarize
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill configures the installation of the
summarizecommand-line utility from a third-party Homebrew tap (steipete/tap/summarize). - [COMMAND_EXECUTION]: The skill instructs the agent to execute the
summarizebinary to process URLs, local files, and transcripts. - [PROMPT_INJECTION]: The skill ingests and summarizes data from external sources such as web pages and YouTube transcripts, which creates a surface for indirect prompt injection where malicious instructions embedded in the source material could attempt to influence the agent.
- Ingestion points: Data is ingested from user-provided URLs, YouTube video transcripts, and local file paths.
- Boundary markers: The instructions do not specify the use of delimiters or warnings to the agent regarding untrusted content in the summarized output.
- Capability inventory: The skill possesses the capability to execute the
summarizeCLI tool. - Sanitization: There is no mention of sanitization or filtering of the content retrieved from external sources before it is processed.
Audit Metadata