cloudflare-agents
Build AI agents on Cloudflare Workers with MCP integration, tool use, and LLM providers.
62
52%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/cloudflare-agents/skills/cloudflare-agents/SKILL.mdSecurity
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.90). The skill's browser/scraping feature clearly fetches arbitrary public URLs supplied to the agent (see templates/browser-agent.ts and references/advanced-features.md: onRequest / scrapeUrl / batch-scrape which call page.goto(url) and then pass page HTML into extractData/OpenAI), so untrusted third‑party page content is ingested and interpreted by an LLM as part of the workflow, enabling indirect prompt injection.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.80). The BrowserAgent fetches arbitrary, user-supplied web pages at runtime via puppeteer.page.goto(url) and injects the fetched HTML into a prompt sent to the OpenAI API (https://api.openai.com/v1/chat/completions), so external websites can directly influence model instructions/outputs at runtime.
- Repository
- secondsky/claude-skills
- Commit
90d6bd7
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.