ClawHub
Back to skill

Security audit

pet-food-calculator

Security checks for vulnerabilities and agentic risk

Overview

This is a local pet-feeding calculator with some overstated documentation, but no evidence of hidden access, exfiltration, persistence, or destructive behavior.

Install only if you are comfortable running a local Python pet-feeding calculator. Treat its veterinary guidance as informational, not a substitute for a vet, and be aware that some advertised features are not actually implemented. If using --json, point it at a deliberate workspace file because an existing file at that path may be overwritten.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The skill description overstates and mismatches actual behavior, including claiming breed/body-condition inputs, multi-food cost comparison, and multi-pet scheduling that are not implemented, while also omitting the undeclared file-output capability. This is dangerous because users and orchestrators may make trust and authorization decisions based on the declared behavior, leading to misleading health guidance and unexpected file writes.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding

The skill advertises no explicit tool scope while the described usage implies shell execution and file read/write behavior. Missing capability declarations weaken least-privilege controls and can cause the agent platform or reviewer to underestimate what the skill is able to do, especially because JSON output to a file is documented.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/test_pet_food_calculator.py (reported line 26)May include surrounding context.

python
def run(*args):
    return subprocess.run([sys.executable, str(SCRIPT), *args],
                          capture_output=True, text=True)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This code performs a file write via Path.write_text(), which can modify or overwrite user data. While the --json flag implies output generation and the script prints the destination afterward, there is no confirmation prompt or explicit warning in the help text/docstring that an existing file may be overwritten.

Content

No source excerpt is available for this finding.