ClawHub
Back to skill

Security audit

PC Game Deals

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple PC game deal lookup, but its shell command templates place user-controlled values directly into executable commands without validation or safe URL parameter handling.

Review this before installing. The skill's purpose is coherent, but agents should not run the shown commands by directly replacing GAME_NAME or GAME_ID with raw user text. Use safe argument handling such as curl --get with --data-urlencode, validate IDs, and keep responses in the user's preferred language.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:30
Finding

Command Injection Through Unsafe User-Controlled URL Parameter Interpolation

Content
View full analysis
Remediation
View remediation
&2 exit 1 ;; esac curl --fail --silent --show-error --get \ "https://www.cheapshark.com/api/1.0/games" \ --data-urlencode "id=${GAME_ID}" | jq '{ cheapest: .cheapestPriceEver.price, current: .deals | map({store: .storeID, price: .price}) }' ``` Additionally: 1. Explicitly instruct the agent never to perform textual substitution of user input into executable shell source. 2. Use process argument arrays instead of a shell when the host implementation supports them. 3. Apply allowlist validation to identifiers and reasonable length limits to game titles. 4. Retain `curl --fail --silent --show-error` so HTTP failures are visible without exposing unnecessary output. 5. Run the Skill with least privilege and restrict filesystem, credential, and network access to reduce the impact of any command-execution flaw. ]]>

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill hardcodes Chinese-language output strings in its example commands, which can cause the agent to respond in Chinese even when the user did not request that language. This is a prompt/quality issue rather than code execution, but it can override user expectations, reduce usability, and create opportunities for subtle instruction interference if skill-authored formatting is treated as authoritative.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.