summarize

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill manages the installation of the 'summarize' command-line utility through the Homebrew package manager using the 'steipete/tap/summarize' formula.- [COMMAND_EXECUTION]: The skill invokes the 'summarize' binary to process user-supplied inputs, including website URLs, local file paths, and YouTube links.- [DATA_EXFILTRATION]: The skill relies on sensitive environment variables for API authentication (such as OPENAI_API_KEY and GEMINI_API_KEY) and accesses a local configuration file at '~/.summarize/config.json'. It also possesses the capability to read local files specified by the user for the purpose of summarization.- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves processing untrusted data from external sources, which presents a risk of indirect prompt injection.
  • Ingestion points: Web content from URLs, YouTube video transcripts, and local file data (SKILL.md).
  • Boundary markers: No explicit delimiters are specified to separate the fetched data from the agent's internal instructions.
  • Capability inventory: Shell execution of the 'summarize' CLI binary (SKILL.md).
  • Sanitization: The instructions do not describe any sanitization or validation of the external content before it is processed by the language model.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 01:08 AM