summarize
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
summarizebinary via a third-party Homebrew tap (steipete/tap/summarize). - [COMMAND_EXECUTION]: Executes the
summarizecommand-line utility with various arguments including user-provided URLs and file paths. - [PROMPT_INJECTION]: This skill presents a surface for indirect prompt injection (Category 8) because it fetches and processes untrusted content from the web to be summarized by the agent.
- Ingestion points: Untrusted content enters the context through web URLs, YouTube transcripts, and local file contents (e.g., PDFs).
- Boundary markers: Absent; there are no instructions to use delimiters or warnings to ignore malicious instructions embedded in the processed data.
- Capability inventory: The
summarizetool has the capability to perform network requests and access the local file system. - Sanitization: No sanitization, escaping, or validation of the fetched external content is described or implemented.
Audit Metadata