ClawHub
Back to skill

Security audit

Pincer

Security checks across malware telemetry and agentic risk

Overview

Pincer appears to be a legitimate security wrapper, but it needs Review because its safety gate can run install actions before scanning in a fallback path and relies on an unpinned external scanner.

Install only if you are comfortable using a best-effort security wrapper rather than a strict pre-install barrier. Consider setting `autoApprove` to `never`, reviewing `~/.config/pincer/config.json`, and avoiding the install command for high-risk third-party skills until the fallback install-before-scan behavior is removed and mcp-scan is pinned.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill declares and installs shell-executable functionality via an install script and a wrapper binary, but no explicit permissions are declared in the skill metadata. That mismatch can weaken user awareness and policy enforcement because the skill is capable of executing shell actions and modifying the user's PATH-visible environment.

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The script executes `uvx mcp-scan@latest`, which fetches and runs a remote package at install/scan time without version pinning or integrity verification. That creates a supply-chain execution path where a compromised upstream package, malicious update, or dependency confusion event could lead to arbitrary code execution on the user's machine under the guise of security scanning.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
case "$risk_level" in
    clean)
      local auto_approve
      auto_approve=$(jq -r '.autoApprove // "clean"' "$CONFIG_FILE")
      if [[ "$auto_approve" == "clean" ]]; then
        info "Auto-approved (clean + trusted config)."
Confidence
81% confidence
Finding
auto_approve

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
case "$risk_level" in
    clean)
      local auto_approve
      auto_approve=$(jq -r '.autoApprove // "clean"' "$CONFIG_FILE")
      if [[ "$auto_approve" == "clean" ]]; then
        info "Auto-approved (clean + trusted config)."
      else
Confidence
81% confidence
Finding
auto_approve

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
case "$risk_level" in
    clean)
      local auto_approve
      auto_approve=$(jq -r '.autoApprove // "clean"' "$CONFIG_FILE")
      if [[ "$auto_approve" == "clean" ]]; then
        info "Auto-approved (clean + trusted config)."
      else
Confidence
81% confidence
Finding
autoApprove

Session Persistence

Medium
Category
Rogue Agent
Content
label: "Install pincer to PATH"
        script: |
          chmod +x "${SKILL_DIR}/scripts/pincer.sh"
          mkdir -p ~/.local/bin
          ln -sf "${SKILL_DIR}/scripts/pincer.sh" ~/.local/bin/pincer
          echo ""
          echo "✅ pincer installed!"
Confidence
86% confidence
Finding
mkdir -p ~/.local/bin ln -sf "${SKILL_DIR}/scripts/pincer.sh" ~/.local/bin/pincer echo "" echo "✅ pincer installed!" echo "" echo "Make sure ~/.local/

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.