Back to skill

Security audit

Pp Olx

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly transparent about driving an OLX public API CLI, but it asks agents to install mutable third-party code and exposes broad output delivery to files or arbitrary webhooks.

Install only if you trust the Printing Press npm package and the OLX CLI publisher. Prefer pinning and verifying the installer/CLI version before use, avoid `--deliver webhook:<url>` unless you intentionally want results sent to that endpoint, and review file output paths before allowing writes.

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:18
Finding

Unpinned Third-Party Installer Executes Mutable Supply-Chain Code

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 18–24
Vulnerability Type: Unpinned third-party dependency installation and execution
Risk Level: Medium

Vulnerable Code

markdown
This skill drives the `olx-pp-cli` binary. **You must verify the CLI is installed before invoking any command from this skill.** If it is missing, install it first:

1. Install via the Printing Press installer:
   ```bash
   npx -y @mvanhorn/printing-press install olx --cli-only
  1. Verify: olx-pp-cli --version
text

### Technical Analysis

The installation command invokes `npx` with automatic confirmation and does not specify an exact package version or integrity digest. Consequently, the code executed depends on whichever release of `@mvanhorn/printing-press` the npm registry resolves at installation time. The installer then retrieves or installs the separate `olx-pp-cli` executable, whose version and checksum are likewise unspecified.

This creates a mutable supply-chain trust path: reviewing the Skill does not establish which installer code or CLI binary will execute later. Compromise of the package publisher, npm artifact, transitive dependency, installer-controlled release source, or distribution process could turn the documented setup procedure into arbitrary code execution. Package lifecycle scripts may also execute during `npx` package preparation.

The issue is classified as insecure dependency handling rather than confirmed embedded malware. The repository contains only `SKILL.md`; it does not contain the installer or CLI implementation, so no malicious behavior in those external components can be established from the audited artifact.

### Attack Path

1. An attacker compromises the npm publisher account, package release process, a relevant dependency, or an installer-controlled binary source.
2. The attacker publishes or serves a malicious artifact under the expected package or CLI identity.
3. An Agent loads this Skill on a system where
...[truncated 1138 chars]
Remediation
View remediation

Remediation Suggestions

  1. Pin @mvanhorn/printing-press to an exact reviewed version rather than relying on registry resolution:
    bash
    npx -y @mvanhorn/printing-press@X.Y.Z install olx --cli-only
    
  2. Pin the exact olx-pp-cli release installed by the Printing Press tool.
  3. Publish official SHA-256 checksums or signed provenance for installer and CLI artifacts, and verify them before execution.
  4. Prefer a documented official release source with signature verification over a dynamically resolved installer chain.
  5. Use a lockfile and integrity metadata where npm-based installation is unavoidable.
  6. Disable or strictly review package lifecycle scripts where operationally possible.
  7. Run installation in a sandbox or least-privileged environment without unrelated credentials or sensitive filesystem access.
  8. Document the trusted publisher, release URL, expected package scope, supported version, signature identity, and verification procedure.
  9. Verify more than command availability: olx-pp-cli --version should be checked against an explicit approved version and the binary against a published digest or signature.
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest describes a narrow read-only OLX public API skill, but the documented CLI supports broader capabilities including local file writes and arbitrary webhook delivery. This mismatch can mislead users or orchestrators into granting trust appropriate for passive API access while the tool can also move data off-host or write to disk.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The skill instructs agents to install and execute an unpinned package via npx, which allows whatever version is current at execution time to run code on the host. That creates a supply-chain risk: a compromised publisher account, malicious new release, or dependency hijack could lead to arbitrary code execution during installation.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

--deliver webhook:<url> enables command results to be POSTed to arbitrary destinations, which is broader than the stated purpose of querying a public OLX API. In an agent setting, this creates a clear exfiltration channel: fetched data, local-store results, or unexpected command output can be sent to attacker-controlled endpoints.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill documents arbitrary webhook posting but does not prominently warn that command output may contain sensitive or unexpectedly scoped data and will be transmitted to external URLs. In an agent context, lack of such warning increases the chance of accidental privacy breaches or deliberate prompt-driven exfiltration.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

--deliver file:<path> allows writing command output to arbitrary filesystem paths, which exceeds the skill's stated purpose of querying a public API. While less severe than webhook exfiltration, it still broadens the trust boundary and can overwrite or place data in unintended locations if an agent is manipulated.

Content

No source excerpt is available for this finding.