ClawHub
Back to skill

Security audit

Cincopa

Security checks for vulnerabilities and agentic risk

Overview

The skill is mainly a Cincopa reader, but its setup instructions tell users to run an unverified remote installer directly in a shell.

Review the setup path before installing. If the oo CLI is already installed and trusted, the Cincopa read actions are straightforward; if not, avoid running the pipe-to-shell installer blindly and prefer a verified installer or documented package source.

A.I.G

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:58
Finding

Unverified Remote Installer Execution Through Shell Pipelines

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 58–62
Vulnerability Type: Remote payload retrieval and execution
Risk Level: High

The first-time setup instructions download installation scripts from a mutable external URL and immediately execute the responses:

bash
curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
powershell
irm https://cli.oomol.com/install.ps1 | iex           # Windows PowerShell

Technical Analysis

Both installation methods combine network retrieval and code execution in a single pipeline. The downloaded scripts are not version-pinned, saved for inspection, checked against a cryptographic digest, or verified using a trusted digital signature.

HTTPS protects the connection in transit but does not establish that the current response is the same payload that existed when the Skill was audited. Compromise of the hosting service, publishing account, DNS or certificate trust chain could therefore replace the installer with arbitrary code.

Installing the CLI may be necessary when it is absent, but immediate execution of an unverified remote response exceeds the minimum privileges needed to provide installation guidance. The Skill could instead direct the user to a pinned, independently verifiable package. The PowerShell command presents the same underlying vulnerability as the Bash command.

Attack Path

  1. A user requests a Cincopa operation through the Skill.
  2. The required oo CLI is unavailable, causing the Agent or user to follow the first-time setup instructions.
  3. An attacker compromises or gains control over the remote installer response or its delivery infrastructure.
  4. curl or irm retrieves the attacker-controlled response.
  5. The pipeline passes the response directly to Bash or Invoke-Expression without verification or inspection.
  6. The malicious response executes with the privileges of the account running the install ...[truncated 677 chars]
Remediation
View remediation

Remediation Suggestions

  • Remove both direct pipe-to-shell installation commands.

  • Use a version-pinned release artifact or a trusted operating-system package manager.

  • Download the installer to a local file without executing it immediately.

  • Validate the artifact using a publisher signature or a cryptographic checksum obtained through an independently trusted channel.

  • Allow the user to inspect the downloaded file and require explicit approval before execution.

  • Document the exact files, permissions, and system changes performed by the installer.

  • Run installation with ordinary user privileges unless a specific, documented operation requires elevation.

  • Prefer instructions resembling the following verified workflow:

    bash
    curl -fL -o oo-install.sh https://trusted.example/path/to/versioned/oo-install.sh
echo '<expected-sha256>  oo-install.sh' | sha256sum --check -
less oo-install.sh
bash oo-install.sh

  • Apply an equivalent download, signature-validation, review, and separate-execution workflow on Windows rather than using Invoke-Expression.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill recommends installing software via a shell pipeline that fetches a remote script and executes it immediately (curl ... | bash). If the remote host, transport path, or served script is compromised, the user or agent could execute arbitrary code with local privileges; in this skill context, that risk is amplified because the command is presented as a troubleshooting step within operational instructions.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest and description frame this skill as only for searching and reading Cincopa data, but the body instructs the agent to handle write and destructive actions too. That mismatch can cause downstream policy engines, users, or orchestrators to trust the skill as read-only when it may perform state-changing operations, increasing the risk of unintended modifications.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation text says to use this skill for ANY Cincopa request, which is overly broad and may trigger the skill for vague mentions of Cincopa without sufficient task scoping. In an agent environment, broad routing rules can cause unintended tool execution or bypass more appropriate safeguards for specific operations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.