summarize
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill prompts for the installation of the
summarizeutility via a Homebrew tap (steipete/tap/summarize). This is a legitimate external dependency required for the skill's core functionality. - [COMMAND_EXECUTION]: The skill instructions direct the agent to execute the
summarizecommand in the shell to process user-provided inputs like URLs and file paths. This behavior is consistent with the skill's stated purpose. - [PROMPT_INJECTION]: As the skill is designed to ingest and process untrusted external content (webpages and transcripts), it possesses a surface for indirect prompt injection.
- Ingestion points: Content is retrieved from arbitrary URLs, YouTube transcripts, and local files provided by the user.
- Boundary markers: The skill does not define specific delimiters to isolate the ingested content from the agent's instructions.
- Capability inventory: The skill facilitates the execution of CLI commands and the handling of file system paths.
- Sanitization: No explicit sanitization or validation of the retrieved content is performed within the skill definition.
Audit Metadata