Back to skill

Security audit

Power Cad Drafter

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-aligned overall, but its advertised automated electrical code audit is underimplemented and contains a concrete logic error that can falsely pass a safety-relevant design.

Review before installing or relying on this skill. It should not be used as an authoritative electrical compliance checker until the transformer-capacity bug is fixed, the missing end-to-end workflow is implemented or clearly documented, dependency versions are pinned, and all generated designs receive independent engineering review.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:14
Finding

Unpinned Third-Party Dependencies Permit Supply-Chain Substitution

Content
View full analysis
Remediation
View remediation
--hash=sha256: PyYAML== --hash=sha256: ``` Then install with: ```bash python3 -m pip install --require-hashes -r requirements.txt ``` ]]>

T09 · Insecure Skill Coding Practices

Error
Location
scripts/audit_engine.py:45
Finding

Incorrect Transformer Capacity Branch Can Produce False Compliance Results

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (8)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared purpose promises automatic audit and survey-data-driven processing, but the reported implementation does not actually implement those capabilities. Security-wise, this is a trust-boundary problem: a misleading interface can cause operators to rely on missing validation or analysis steps, producing unsafe engineering outputs while believing compliance checks occurred.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared purpose promises automatic audit and survey-data-driven processing, but the reported implementation does not actually implement those capabilities. Security-wise, this is a trust-boundary problem: a misleading interface can cause operators to rely on missing validation or analysis steps, producing unsafe engineering outputs while believing compliance checks occurred.

Content

No source excerpt is available for this finding.

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 44)May include surrounding context.

md
### 2. Design Parameter Inference
Infer design parameters per the company code:

| Item | Input | Output Rule |
|------|-------|-------------|
| Load calculation | Area, units, load density | Demand factor method |
| Transformer | Load, location | Dry/oil, D,yn11, standard capacity |

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill describes reading a company code file and generating multiple local output files, but it declares no explicit tool scope or permissions. In an agent environment, missing permission boundaries can allow undeclared file read/write behavior to occur implicitly, reducing reviewability and increasing the chance of unintended filesystem access.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger section activates on general conditions like providing survey data or requesting diagram review, which could match many ordinary engineering conversations rather than a narrowly scoped invocation. The file does not provide explicit trigger phrases, exclusions, or negative examples to clarify when this skill should or should not be used.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This Python file contains natural-language descriptions, comments, report headers, and console output entirely in Chinese, including the generated report content. The skill does not provide any user opt-in, locale selection, or explicit documentation that the tool is intentionally restricted to a Chinese-language/regional compliance context.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest says the skill auto-generates CAD drawings from survey data and auto-audits against power codes, which describes drawing generation and compliance analysis. This file not only performs auditing but also persists a Markdown report to an arbitrary output path, which is a separate file-writing behavior not stated in the manifest description.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The title and governing-standard note are entirely in Chinese, with no indication that other languages are supported or that the locale restriction is optional. Under the policy, language constraints should either offer user choice or be clearly documented as a justified region-specific requirement.

Content

No source excerpt is available for this finding.