summarize
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the
summarizecommand-line utility to perform its primary function. - [EXTERNAL_DOWNLOADS]: The skill defines installation steps that download a binary from a third-party Homebrew repository (
steipete/tap/summarize). - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it summarizes data from untrusted external sources.
- Ingestion points: Untrusted data enters the context via URLs and file paths passed to the
summarizecommand inSKILL.md. - Boundary markers: The skill lacks delimiters or instructions to ignore commands within the summarized content.
- Capability inventory: The skill enables subprocess execution of the
summarizebinary as shown in the examples. - Sanitization: There is no evidence of sanitization or filtering of external content before it is processed.
Audit Metadata