HN Digest
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
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.
A user expecting only HN links may also trigger image generation and possible third-party API usage or cost.
The frontmatter presents the skill as an HN post digest, but the body mandates an additional generated image, which can cause unexpected provider/API use.
description: "Fetch and send Hacker News front-page posts on demand... Sends N ... posts as individual messages with Title + Link." ... "After the post messages, send one final message that is the generated image."
Clearly disclose image generation in the description and make it optional or require confirmation before calling the image provider.
The skill may use a stored Gemini/Nano Banana credential and consume that account's quota or billing without the credential requirement being visible in the registry metadata.
The script reads an API key from the environment or the user's OpenClaw config, even though the metadata declares no required credentials, env vars, or config paths.
env_key = (os.environ.get("GEMINI_API_KEY") or "").strip() ... Path.home() / ".openclaw" / "openclaw.json" ... get("nano-banana-pro", {}).get("apiKey")Declare the credential and config path explicitly, avoid borrowing another skill's stored key, and ask the user before using a provider credential.
First use can run newly downloaded package code that was not surfaced during installation review.
The skill downloads and installs unpinned dependencies at runtime, despite having no install spec or declared binary/package requirements.
python3 -m venv "$VENV_DIR" "$PY" -m pip install --quiet --disable-pip-version-check google-genai pillow
Move dependencies into an explicit install spec, pin versions or provide a lockfile, and disclose required runtimes such as node, python3, and pip.