ClawHub
Back to skill

Security audit

founder-ledger-tracker

Security checks for vulnerabilities and agentic risk

Overview

This is a small local Python goal and budget reminder tool with disclosed file writes and no hidden network, credential, or persistence behavior.

Before installing, understand that the skill creates and updates a local JSON state file in the current directory by default, and --force can overwrite an existing tracker state file. It does not appear to send data externally or access credentials.

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 (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The declared description is for the end-user tracker utility itself, but the provided code chunk is not that utility; it is a test module exercising and validating the utility and related metadata. While the tests reference behavior consistent with the declared tracker (goal tracking, deadline and budget guard, reminder text, exit codes), the actual code's primary purpose is automated verification, including extra capabilities unrelated to the declared runtime tool such as frontmatter validation and documentation wording checks. Therefore the supplied code chunk does not accurately represent the declared purpose.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

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 · tests/test_tracker.py (reported line 99)May include surrounding context.

python
self.tmp.cleanup()

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