ClawHub
Back to skill

Security audit

Tripadvisor

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its Tripadvisor lookup purpose, but its setup instructions include directly executing remote installer scripts, which warrants review before installing.

Install only if you are comfortable using OOMOL as the intermediary for Tripadvisor data. Do not blindly run the provided remote installer commands; use a verified official installation path, inspect the installer, and prefer checksum or signature verification before executing anything.

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:55
Finding

Unverified Remote Installer Execution Through Shell Interpreters

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 55–64
Vulnerability Type: Remote payload retrieval and execution
Risk Level: Critical

Vulnerable Code

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

The first-time setup instructions download mutable scripts from cli.oomol.com and immediately execute the responses with Bash or PowerShell. The process does not pin a release, save the scripts for inspection, verify a cryptographic signature, or compare them against trusted checksums.

HTTPS protects data in transit but does not establish that the hosted scripts are trustworthy or immutable. Compromise of the hosting infrastructure, publisher account, domain, DNS path, or content delivery system could replace either installer with an arbitrary payload. Because the project only contains SKILL.md, the actual installer behavior cannot be audited from the submitted artifact.

Although installing the required CLI may support the declared Tripadvisor functionality, automatic execution of unverified remote content exceeds the minimum privilege needed to invoke read-only Tripadvisor connector actions. Installation should be a separate, explicit, and verifiable user-controlled operation.

Attack Path

  1. The oo command is unavailable on the target system.
  2. The Agent or user follows the documented first-time setup instructions.
  3. The shell retrieves a mutable installer from cli.oomol.com.
  4. A compromised server or delivery path supplies attacker-controlled content with a successful HTTP response.
  5. Bash or PowerShell executes that content immediately without inspection or integrity verification.
  6. The payload performs arbitrary actions with the privileges of the invoking Agent or user.

Impact Assessment

Successful exploitation provides arbitrary code execution under the invo ...[truncated 424 chars]

Remediation
View remediation

Remediation Suggestions

  1. Remove all pipe-to-interpreter installation commands, including both curl | bash and irm | iex.
  2. Direct users to an official, signed package-manager distribution where possible.
  3. Pin installation instructions to a specific reviewed CLI version rather than a mutable latest installer.
  4. Download the installation artifact to a local file without executing it automatically.
  5. Publish and verify a cryptographic signature from a trusted release key and a hard-coded SHA-256 checksum obtained through an independent trusted channel.
  6. Allow the user to inspect the downloaded file and require explicit approval before execution.
  7. Run installation with ordinary user privileges unless a narrowly defined operation requires elevation; do not request broad administrative access by default.
  8. Document the files, network destinations, and system changes produced by installation.
  9. Keep setup separate from normal Skill execution. Authentication or missing-command errors should result in instructions to the user, not autonomous software installation.
  10. Prefer commands conceptually equivalent to the following verified workflow:
bash
curl -fL -o oo-installer.sh "https://trusted.example/releases/vX.Y.Z/install.sh"
echo "<trusted-sha256>  oo-installer.sh" | sha256sum -c -
# Inspect the file and obtain explicit user approval before:
bash oo-installer.sh

A publisher signature should be verified in addition to a checksum wherever possible.

SkillSpector

Vulnerability Patterns
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs users to install software via a remote script piped directly to a shell (curl ... | bash), which is a classic supply-chain and arbitrary code-execution risk. If the install endpoint, transport, hosting account, or upstream release process is compromised, a user following the skill could execute attacker-controlled code on their machine.

Content

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

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The phrase "Use this skill for ANY Tripadvisor request" is extremely broad and could match many ordinary references to Tripadvisor without clarifying scope, exclusions, or concrete trigger examples. The description also lacks negative examples or tighter constraints on when the skill should and should not be invoked.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.