summarize
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
summarizecommand-line tool with user-specified inputs such as web links and local file paths. - [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
summarizebinary from a third-party Homebrew repository (steipete/tap/summarize). - [INDIRECT_PROMPT_INJECTION]: The skill contains a risk surface for indirect prompt injection as it processes content retrieved from external, potentially untrusted sources.
- Ingestion points: URL and file path arguments passed to the
summarizecommand within the skill instructions. - Boundary markers: There are no explicit instructions or delimiters used to separate the content being processed from the agent's internal operational logic.
- Capability inventory: The skill's primary tool,
summarize, performs network requests and reads local files to extract content for the LLM. - Sanitization: The skill does not define specific sanitization or filtering protocols for the data fetched from the provided inputs before processing.
Audit Metadata