summarize
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs an external binary from a third-party Homebrew tap (steipete/tap/summarize) as defined in the metadata section.
- [COMMAND_EXECUTION]: The agent is instructed to run the 'summarize' command to process user-specified URLs and file paths.
- [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface through its core functionality. 1. Ingestion points: External URLs, local files, and YouTube transcripts (as described in SKILL.md). 2. Boundary markers: The instructions lack delimiters or explicit warnings to the agent to ignore instructions embedded in the ingested content. 3. Capability inventory: The skill executes a CLI tool that performs network requests to external LLM APIs. 4. Sanitization: There is no evidence of sanitization or validation of the content before it is processed by the agent.
Audit Metadata