Canghe Danger Gemini Web
CheckedAnalyzes Gemini web search results to identify potential risks, threats, and vulnerabilities related to specified topics.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add freestylefly/canghe-skills --skill canghe-danger-gemini-web -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
freestylefly
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned freestylefly/canghe-skills at dd0bf35595.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- dd0bf35595
- Scanned
- 1 file, 144 lines
About this skill
What it does
The canghe-danger-gemini-web skill allows AI agents to access and interact with Gemini web search results. It provides a way for agents to retrieve information from the internet, summarize content found online, and potentially use that information in subsequent actions or responses. This enables agents to perform tasks requiring up-to-date data and external knowledge.
When to use it
- Research Tasks: An agent needs to gather current information about a specific topic (e.g., "What are the latest developments in AI safety?").
- Content Summarization: You want an agent to quickly summarize articles or web pages found through search (e.g., "Summarize this article: [URL]").
- Data Extraction: An agent needs to extract specific data points from a website, like product pricing or event dates.
- Real-time Updates: The agent requires the most recent information available online for decision making.
Key capabilities
- Gemini web search integration
- Content retrieval from URLs
- Summarization of retrieved content
Example prompts
- "Search Gemini for 'best hiking trails near Denver' and list the top 3 results."
- "Find the current price of Bitcoin using Gemini web search, then tell me if it has increased or decreased in the last 24 hours."
- "Summarize the main points from this article: [URL]"
Tips & gotchas
The quality of results depends on the clarity and specificity of your prompts. Ensure that the agent has access to a Gemini-compatible environment for optimal performance.