Back to skill

Security audit

Complex Mathematics Engine

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent remote math tool, but its broad activation terms and unpinned setup-install commands deserve review before use.

Install only if you are comfortable sending math expressions to AgentPMT and spending the listed credits. Prefer pinned or verified install sources for the referenced setup skills, avoid putting secrets or sensitive business data in expressions, and consider disabling or narrowing automatic activation for generic calculation requests.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:187
Finding

Unpinned Third-Party Skill Installation Creates a Supply-Chain Risk

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 187–201
Vulnerability Type: Unpinned and unverified third-party dependency installation
Risk Level: Medium

markdown
Core AgentPMT setup skills:
- What AgentPMT is: ../what-is-agentpmt
  - ClawHub page: https://clawhub.ai/agentpmt/what-is-agentpmt
  - OpenClaw install: `openclaw skills install what-is-agentpmt`
  - skills.sh install: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`
- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup
  - ClawHub page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup
  - OpenClaw install: `openclaw skills install agentpmt-account-mcp-rest-api-setup`
  - skills.sh install: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`

skills.sh install script:

```bash
npx skills add AgentPMT/agent-skills --skill what-is-agentpmt
npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup
text

### Technical Analysis

The documented installation commands retrieve skills from mutable external distribution channels without specifying a package version, immutable repository commit, checksum, or signature. Invoking `npx` can also retrieve and execute package tooling that is not pinned in the instructions.

Consequently, the effective content installed by these commands can change after this Skill has been reviewed. A compromise of the package registry, upstream repository, publisher account, or skill distribution channel could cause users to receive content different from the audited version.

The risk is elevated because the downloaded components concern AgentPMT account, MCP, and REST configuration. Such setup components may operate in an authentication-sensitive context. The audited project does not itself contain evidence that the current upstream packages are malicious; the vulnerability is the absence of integrity and
...[truncated 1715 chars]
Remediation
View remediation

Remediation Suggestions

  1. Pin every installation dependency to a reviewed, immutable package version and repository commit.
  2. Replace mutable commands with version-qualified forms supported by the relevant installer.
  3. Publish cryptographic checksums or signed release metadata and require verification before installation.
  4. Configure package tooling to enforce lockfiles, signature verification, and reproducible dependency resolution where supported.
  5. Avoid executing remotely retrieved setup tooling through npx unless the exact package version and integrity are fixed.
  6. Review the account-setup skills separately because they operate near authentication and API configuration boundaries.
  7. Run installation with a non-privileged account in an isolated environment and grant only the filesystem and network access required for setup.
  8. Do not automatically reinstall or update solely because the document's freshness period has elapsed; require explicit review and approval of the new version.
  9. Document the expected publisher identity, release version, commit hash, and verification procedure alongside each installation command.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (10)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description/discovery terms include very broad triggers such as calculate and expression. In an agent environment, generic activation terms can cause this remote tool to be selected unexpectedly, sending user data or prompts to an external service when a simpler local response would have sufficed.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation keywords are overly generic and may match routine requests unrelated to this product. Because this skill routes to AgentPMT-hosted remote calls, unintended invocation can leak user-provided content externally and incur unnecessary paid actions.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The skill instructs users to run npx skills add ... without pinning an exact package version or immutable source. That creates a supply-chain risk: a later compromised or incompatible package release could be fetched and executed at install time.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

This line repeats an unpinned npx skills add ... installation path. Because npx resolves packages dynamically, users may execute changed code in the future, exposing them to supply-chain compromise.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The install script includes npx skills add without a fixed version, so the fetched installer behavior can change over time. In a skill ecosystem, that increases risk because users may trust and run commands copied directly from the skill documentation.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

This is another floating npx skills add ... command that can retrieve whatever package version is current at execution time. If the upstream package or dependency chain is hijacked, users could run attacker-controlled install code.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

The reference section again recommends an unversioned npx skills add ... command. Repetition increases exposure because users are more likely to copy-paste it, normalizing execution of mutable remote code.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

Like the other npx skills occurrences, this line lacks version pinning and can pull updated code silently. That is a real supply-chain weakness, especially in setup instructions that users may execute verbatim.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 253)May include surrounding context.

md
- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`)
- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`)
- Marketplace product: https://www.agentpmt.com/marketplace/complex-mathematics-engine
- AgentPMT main MCP server: https://api.agentpmt.com/mcp/
- AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 254)May include surrounding context.

md
- What AgentPMT is: ../what-is-agentpmt (ClawHub: `what-is-agentpmt`, page: https://clawhub.ai/agentpmt/what-is-agentpmt; skills.sh: `npx skills add AgentPMT/agent-skills --skill what-is-agentpmt`)
- AgentPMT account MCP/REST setup: ../agentpmt-account-mcp-rest-api-setup (ClawHub: `agentpmt-account-mcp-rest-api-setup`, page: https://clawhub.ai/agentpmt/agentpmt-account-mcp-rest-api-setup; skills.sh: `npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup`)
- Marketplace product: https://www.agentpmt.com/marketplace/complex-mathematics-engine
- AgentPMT main MCP server: https://api.agentpmt.com/mcp/
- AgentPMT REST invoke endpoint: https://api.agentpmt.com/products/purchase

Static analysis

No suspicious patterns detected.