Back to skill

Security audit

landlord-deposit-defender

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local tenant deposit dispute helper with disclosed, purpose-aligned behavior and no evidence of hidden network access, persistence, credential handling, or destructive actions.

Before relying on the generated letter, verify the current law and deposit deadlines for your jurisdiction and review all dollar amounts and facts. The skill appears safe to install from a security perspective, but it is decision support, not legal advice.

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
Vulnerability Patterns
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (9)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 21)May include surrounding context.

md
Four commands in `scripts/deposit_defender.py`:

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md
Four commands in `scripts/deposit_defender.py`:

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

md
Four commands in `scripts/deposit_defender.py`:

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 63)May include surrounding context.

md
Four commands in `scripts/deposit_defender.py`:

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

md
Four commands in `scripts/deposit_defender.py`:

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 73)May include surrounding context.

md
Four commands in `scripts/deposit_defender.py`:

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill invokes local code via python3 scripts/deposit_defender.py and writes output files, but the manifest does not declare any permissions or allowed-tools scope. That mismatch weakens review and enforcement because an agent or platform may permit broader file/shell access than users expect, increasing the chance of unintended command execution or filesystem exposure.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code generates the entire demand letter using fixed English headings and body text, regardless of user preference or locale. Because the skill supports multiple jurisdictions including Germany and non-US regions, hard-coding one language without opt-in or alternatives is a natural-language locale policy concern.

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_deposit_defender.py (reported line 28)May include surrounding context.

python
def run(args, expect_rc=0):
    """Run the CLI with args; assert returncode matches; return CompletedProcess."""
    global failed
    proc = subprocess.run(
        [PY, SCRIPT] + args, capture_output=True, text=True, timeout=60
    )
    if proc.returncode != expect_rc: