doe-plan

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 6:22 AM UTC
• Version: 1.0.0

Overview

This skill is a disclosed DOE planning workflow that reads user-supplied evidence, uses optional PatSnap retrieval, and writes expected planning artifacts without hidden persistence or unrelated authority.

Install this only where running local Python scripts and creating DOE output files is acceptable. Use a dedicated project/output directory, review PatSnap MCP access before enabling it, and avoid feeding sensitive unpublished data unless the retrieval and storage environment is approved for that data.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (10)

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md

evidence into traceable factor hypotheses, choosing PB/FFD/BBD/CCD designs via scripts/doe_pipeline.py, generating run sheets, and rendering a DOE plan report;

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 35)May include surrounding context.

md

evidence into traceable factor hypotheses, choosing PB/FFD/BBD/CCD designs via scripts/doe_pipeline.py, generating run sheets, and rendering a DOE plan report;

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 102)May include surrounding context.

md

evidence into traceable factor hypotheses, choosing PB/FFD/BBD/CCD designs via scripts/doe_pipeline.py, generating run sheets, and rendering a DOE plan report;

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 114)May include surrounding context.

md

evidence into traceable factor hypotheses, choosing PB/FFD/BBD/CCD designs via scripts/doe_pipeline.py, generating run sheets, and rendering a DOE plan report;

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 125)May include surrounding context.

md

evidence into traceable factor hypotheses, choosing PB/FFD/BBD/CCD designs via scripts/doe_pipeline.py, generating run sheets, and rendering a DOE plan report;

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 144)May include surrounding context.

md

evidence into traceable factor hypotheses, choosing PB/FFD/BBD/CCD designs via scripts/doe_pipeline.py, generating run sheets, and rendering a DOE plan report;

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 157)May include surrounding context.

md

evidence into traceable factor hypotheses, choosing PB/FFD/BBD/CCD designs via scripts/doe_pipeline.py, generating run sheets, and rendering a DOE plan report;

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 94% confidence

Finding

The skill instructs use of shell commands and creation of multiple files, but it does not declare an explicit tool scope such as allowed-tools or permissions. That creates an authorization ambiguity where an agent runtime may grant broader file or shell access than intended, increasing the chance of unsafe command execution, unintended file modification, or misuse of retrieved content during the DOE pipeline.

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/tests/doe_pipeline_test.py (reported line 31)May include surrounding context.

python

def run_script(script: Path, *args: str) -> subprocess.CompletedProcess[str]:
    return subprocess.run(
        [sys.executable, str(script), *args],
        cwd=str(SCRIPTS_DIR),
        capture_output=True,

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 85% confidence

Finding

This code path automatically creates an output directory and writes several artifacts including JSON, CSV, and Markdown files. Although some subcommands print after writing, the run-all entrypoint itself provides no prior disclosure or confirmation before generating multiple files, which is relevant for a code-file missing-warning review.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.