ClawHub
Back to skill

Security audit

attic-insulation-payback

Security checks for vulnerabilities and agentic risk

Overview

This local insulation calculator has no hidden access or persistence, though its savings estimates need independent checking.

Suitable as a rough local calculator. Treat its recommendations as estimates: payback does not model future degradation, comparison-table savings can omit calibration adjustments, and cooling calculations are not implemented. Verify measurements, assumptions, current rebates, and contractor pricing before committing money.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

The advertised degradation-aware payback is implemented as constant-savings simple payback.

Medium
Category
Excessive Agency
Confidence
98% confidence
Finding

The skill advertises degradation-aware payback, but the implementation divides the quote by a single annual savings estimate and uses that result to issue investment recommendations. Although the documentation also calls this simple payback, the broader capability claim can mislead users into treating the result as degradation-adjusted; in a contractor-quote evaluation tool, that mismatch can influence substantial spending decisions.

Content

No source excerpt is available for this finding.

Dynamic attribute access via getattr()

Low
Category
Dangerous Code Execution
Confidence
50% confidence
Finding

Dynamic getattr() with a non-literal attribute name can access arbitrary object attributes, potentially bypassing access controls.

Content

Scanner excerpt · scripts/attic_payback.py (reported line 177)May include surrounding context.

python
cmd_rcheck(a)
    else:
        for req in ("area", "r_current"):
            if getattr(a, req.replace("-", "_")) is None:
                p.error(f"--{req} is required unless --r-check")
        cmd_payback(a)