update

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.90). The URL is a direct raw GitHub link to an install.sh script from an unverified/unknown user and is intended to be executed directly (bash <(curl ...)), which is a high-risk pattern for distributing malware or arbitrary commands.

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly requires executing a remote installer fetched with curl from the public URL https://raw.githubusercontent.com/boshu2/agentops/main/scripts/install.sh, which pulls and runs public/untrusted third-party code that can change agent behavior and therefore enable indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's runtime step runs bash <(curl -fsSL https://raw.githubusercontent.com/boshu2/agentops/main/scripts/install.sh), which fetches and immediately executes remote code from the referenced raw GitHub URL and is required for the update workflow.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). This skill explicitly commands the agent to fetch and execute a remote install script that installs/upgrades skills globally (modifying system/agent state and potentially requiring elevated privileges), so it actively changes the machine and is high risk.