Security audit

Feelgoodbot

Security checks across malware telemetry and agentic risk

Overview

The skill is a disclosed local security-monitoring setup with expected persistence and local alert integration, but users should understand that TOTP protection depends on separate setup and agent integration.

Install only if you trust the upstream feelgoodbot Go project and want persistent local monitoring. Before running setup, review that it installs an unpinned @latest Go binary, creates a baseline, enables Clawdbot webhooks, stores a local webhook secret, restarts the gateway, and starts a daemon. Run and verify the documented TOTP initialization separately if you expect step-up authentication to protect sensitive actions.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 92% confidence
Finding: The skill advertises security-sensitive functionality, including TOTP step-up authentication, but the document mostly provides shell commands and pseudocode rather than an enforceable integration mechanism. In a security skill, this mismatch is dangerous because operators may believe sensitive actions are protected when the protection is only advisory or partially implemented, creating a false sense of security while also modifying related systems such as Clawdbot hooks and a monitoring daemon.

Description-Behavior Mismatch

Medium

Confidence: 92% confidence
Finding: The script performs Clawdbot webhook configuration and gateway restart even though the declared skill purpose is feelgoodbot integrity monitoring and TOTP step-up authentication. This mismatch expands the skill's scope into modifying another system's runtime configuration, which is risky because users may not expect those side effects and may grant trust based on the manifest alone.

Description-Behavior Mismatch

High

Confidence: 97% confidence
Finding: The manifest advertises TOTP step-up authentication, but the script never configures any OTP/TOTP mechanism. This is dangerous because it can create a false sense of protection: operators may believe sensitive actions are gated by step-up authentication when no such control exists.

Missing User Warnings

Medium

Confidence: 85% confidence
Finding: The script writes the Clawdbot webhook secret into a plaintext configuration file under the user's home directory without warning or permission hardening. Storing credentials this way increases the chance of token disclosure through local file access, backups, logs, or overly permissive filesystem settings.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The script enables Clawdbot webhooks, sets a token, and restarts the gateway automatically without explicit user consent. Unannounced security-relevant configuration changes can disrupt existing service behavior, interfere with prior configurations, and create unexpected exposure or operational impact.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.