quantum-cryptography-verification

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The workflow explicitly instructs including the plaintext cqcv_data value inside a CLI command/JSON (acp job create ... --requirements '{"cqcv_data":"..."}'), which would require the LLM to output user secrets verbatim and thus creates an exfiltration risk.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). The URL is a GitHub repository for an unverified/unknown project that instructs users to install and run a CLI (executable code) — while GitHub can be legitimate, installing CLI tools from a low-reputation or unvetted repo carries a notable malware risk until the project, maintainers, releases, and code signatures are verified.

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

• Third-party content exposure detected (high risk: 0.80). The workflow explicitly requires running "acp browse" (step 3) to fetch provider wallet listings from the external ACP ecosystem (and installation from the GitHub repo), which means untrusted third-party provider content is retrieved and used to choose a wallet that directly affects subsequent job creation and behavior.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires installing and running the ACP CLI from https://github.com/Virtual-Protocol/openclaw-acp, a remote repository that would be fetched and executed to perform the runtime acp commands, so external code controls execution.