parallel-web-extract

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). Yes — the skill instructs running a remote shell script (curl | bash) from https://parallel.ai/install.sh, which is a high-risk pattern for malware distribution unless the domain and script are verified and inspected.

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md "URL Extraction" workflow explicitly instructs using parallel-cli extract "$ARGUMENTS" to fetch any URL/webpage and return content verbatim, thus ingesting arbitrary public third-party (potentially user-generated) content that could contain instructions and influence agent behavior.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's setup directs executing a remote installer with "curl -fsSL https://parallel.ai/install.sh | bash", which downloads and runs code to install the required parallel-cli dependency used at runtime, thus executing remote code that the skill depends on.