ckb-ccc-examples-finder

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs runtime fetching of public web content (e.g., GET https://docs.ckbccc.com/en/docs/code-examples.md) and extracting Markdown/embedded code from it, which would be outsider-authored free text ingested into the agent’s LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs fetching external Markdown/source at https://docs.ckbccc.com/en/docs/code-examples.md and the sporeprotocol/dob-cookbook repository (to pull example .md files containing full TypeScript) which would bring remote code/instructions into the agent runtime.