Back to skill

Security audit

Volcengine Skills Finder

Security checks for vulnerabilities and agentic risk

Overview

This skill needs review because status checks can automatically download and run software, and capability gaps can trigger user-wide skill installation.

Review and approve the exact skills before installation, prefer project scope, and use dry-run to inspect the command. Provision a reviewed, pinned CLI and skill source; status checks should use that local CLI without downloading executable dependencies.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (8)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, shell.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
89% confidence
Finding

The documented installer uses an unversioned npx skills invocation, which can fetch and execute a changing package release with the user's local privileges. This is a CLI dependency rather than an MCP server, but the underlying supply-chain risk is real: a compromised release could access local credentials or modify files, and checking installed skill names afterward would not prevent that execution.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
88% confidence
Finding

Although this helper accepts an argument list and does not invoke a shell, its caller supplies an unversioned npx --yes skills list --json command. Consequently, a nominally read-only status operation can automatically fetch and execute an unreviewed package release with user privileges. This is the same dependency-execution issue as the fallback listing finding, not a separate command-injection vulnerability.

Content

Scanner excerpt · scripts/find_skills.py (reported line 117)May include surrounding context.

python
) -> tuple[subprocess.CompletedProcess[str], Any | None]:
    completed: subprocess.CompletedProcess[str] | None = None
    for _ in range(attempts):
        completed = subprocess.run(command, capture_output=True, text=True, check=False)
        if completed.returncode != 0:
            return completed, None
        try:

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
88% confidence
Finding

The fallback listing command executes npx --yes skills list without pinning the skills package. If the package is unavailable locally, npx can automatically download and execute a compromised upstream release with the user's privileges, even during an installation-status check. Argument-list execution prevents shell injection, but does not mitigate this dependency supply-chain exposure.

Content

Scanner excerpt · scripts/find_skills.py (reported line 148)May include surrounding context.

python
if isinstance(item, dict) and isinstance(item.get("name"), str)
        }

    completed = subprocess.run(command, capture_output=True, text=True, check=False)
    if completed.returncode != 0:
        detail = completed.stderr.strip() or completed.stdout.strip()
        fail(f"unable to list installed skills: {detail}", completed.returncode)

MCP server referenced without pinned version: 'npx executable'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx executable'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
90% confidence
Finding

Installation invokes the unversioned skills package through npx --yes, allowing automatic execution of an upstream release that has not been pinned or verified by this script. A compromised CLI could access local credentials or modify agent configuration with the invoking user's permissions. Installing skills is an intended capability, and the argument list does not itself introduce shell injection, but the CLI bootstrap creates an additional supply-chain trust boundary.

Content

Scanner excerpt · scripts/find_skills.py (reported line 208)May include surrounding context.

python
return
    if shutil.which("npx") is None:
        fail("npx executable not found; install Node.js to install skills")
    completed = subprocess.run(command, capture_output=True, text=True, check=False)
    if completed.returncode != 0:
        detail = completed.stderr.strip() or completed.stdout.strip()
        fail(f"skills CLI install failed: {detail}", completed.returncode)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
85% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · scripts/find_skills.py (reported line 239)May include surrounding context.

python
catalog: dict[str, Any], agent: str | None, scope: str, as_json: bool
) -> None:
    if shutil.which("npx") is None:
        fail("npx executable not found; install Node.js to inspect installed skills")
    installed_names = installed_skill_names(catalog, agent, scope)
    rows = [
        {