ClawHub

Content Product Analyzer

v1.0.0

produce a commercial teardown of a post, creator profile, product page, landing page, or app page from urls, screenshots, or pasted text. use to infer audien...

⭐ 0· 73·0 current·0 all-time
by@guoxinling
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The skill's name/description (commercial teardown of content/product pages) matches the SKILL.md and README: it accepts URLs, screenshots, and pasted text and asks for evidence modes for optional web verification. No unrelated credentials, binaries, or config paths are requested.
✓
Instruction Scope
Runtime instructions are narrowly scoped to extracting observed facts, making supported inferences, and optionally performing mixed-mode web verification when public URLs or freshness are requested. The workflow explicitly forbids requesting secrets and limits claims from screenshots to visible evidence. It does not instruct the agent to read unrelated system files or access other skills' data.
✓
Install Mechanism
This is instruction-only with no install spec or code to write to disk. That minimizes installation risk; there are no external download URLs or package installs to evaluate.
✓
Credentials
The skill declares no environment variables, secrets, or primary credentials. The README reinforces it should never request API keys/cookies/tokens. The mixed-mode web verification relies on public sources only and does not require extra credentials.
✓
Persistence & Privilege
always is false and there are no indications the skill requests permanent presence or modifies other skills or system-wide settings. It is user-invocable and can be invoked autonomously like normal skills, which is expected.
Assessment
This skill is instruction-only and internally consistent with its stated purpose, but you should consider platform-level privacy: when using mixed-mode the agent will fetch public URLs (that is expected), and any screenshots or pasted text you provide may contain sensitive or identifying information — avoid uploading secrets, API keys, cookies, or private user data. If you want offline-only analysis, choose the "User-provided only" mode. Test the skill first with non-sensitive examples to confirm outputs and citation behavior. Review example prompts in the repo to ensure they match how you plan to use the skill.

Like a lobster shell, security has layers — review code before you run it.

latestvk97fpgzdgjy88ffxcr4z36f1a983hhbgv0.1.0vk97fpgzdgjy88ffxcr4z36f1a983hhbg

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments