lazyweb-growth-experiments

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). This is a direct remote shell script (install.sh) hosted on a personal domain and recommended to be piped into bash, a high-risk pattern for distributing malware or running untrusted code.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill directs users to run an unverified remote installer via "curl ... | bash" (https://www.lazyweb.com/install.sh), a high-risk supply-chain / remote-code-execution pattern that can install backdoors or exfiltrate data.

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

• Third-party content exposure detected (low risk: 0.10). The skill directs the agent to use the lazyweb_search_experiments tool for searching/researching growth ideas, which implies the runtime LLM ingests externally authored free text from the Lazyweb service in response to search results.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs at runtime to run a remote install script via curl and bash, which executes code fetched from https://www.lazyweb.com/install.sh, so the URL is a high-confidence remote-code execution dependency.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly tells the agent to run a remote installer via curl ... | bash, which directly instructs execution of external code that can modify system files or request sudo and thus can compromise the machine state.