Summarize

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This skill appears coherent for summarizing links, videos, and files, but users should notice that it installs an external CLI and may use third-party AI or extraction services.

This skill is reasonable for its stated purpose. Before installing, verify that you trust the Homebrew package source, configure only the API keys you intend to use, and avoid sending confidential files or private URLs to external providers unless that is acceptable for your workflow.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

You would be trusting the external Homebrew package that provides the summarize command.

Why it was flagged

The skill relies on installing an external Homebrew CLI package. That is coherent with a CLI skill, but the executable itself is not included in the provided artifacts.

Skill content
"install": [{ "id": "brew", "kind": "brew", "formula": "steipete/tap/summarize", "bins": ["summarize"] }]
Recommendation

Install only if you trust the Homebrew tap and the summarize project source; keep the CLI updated through normal package-management practices.

#
ASI03: Identity and Privilege Abuse
Low
What this means

The CLI may use your configured model-provider account and could incur usage charges or access whatever privileges that API key grants.

Why it was flagged

The skill documents use of provider API credentials. This is expected for a model-backed summarization CLI and no hardcoded keys or unrelated credential use are shown.

Skill content
Set the API key for your chosen provider: OpenAI: `OPENAI_API_KEY`; Anthropic: `ANTHROPIC_API_KEY`; xAI: `XAI_API_KEY`; Google: `GEMINI_API_KEY`
Recommendation

Use provider keys with the minimum needed scope, monitor usage, and avoid sharing keys in prompts or files.

#
ASI07: Insecure Inter-Agent Communication
Low
What this means

Private documents, URLs, or video transcript content may be sent to third-party services for summarization or extraction.

Why it was flagged

The skill can process local files using external model providers and optional extraction services. This is purpose-aligned, but it means document or URL content may leave the local environment depending on the CLI behavior and selected services.

Skill content
summarize "/path/to/file.pdf" --model google/gemini-3-flash-preview ... Optional services: `FIRECRAWL_API_KEY` for blocked sites; `APIFY_API_TOKEN` for YouTube fallback
Recommendation

Do not use it on confidential files or sensitive links unless you are comfortable with the configured provider and optional services handling that content.