summarize
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
summarizebinary from a third-party Homebrew tap (steipete/tap/summarize). - [COMMAND_EXECUTION]: The skill uses the
summarizecommand-line tool to process URLs, local files, and YouTube links. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external URLs and user-provided local files, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: Arguments passed to the
summarizecommand (URLs, file paths, YouTube links) originating from user input or external web content. - Boundary markers: Absent; the skill instructions do not define delimiters or provide specific instructions to the agent to ignore embedded commands within the extracted summaries.
- Capability inventory: Execution of the
summarizebinary, network access to retrieve content from arbitrary URLs, and read access to the local file system. - Sanitization: Absent; the skill does not specify any validation, filtering, or escaping of the content fetched from external sources before it is processed by the AI.
Audit Metadata