Concept Design — Modular, Legible Software, Architecture in Practice

• Outcome: Pass
• Latest audit: Nov 3, 2026 · 4:14 AM UTC
• Version: 2.0.2

Overview

This skill provides explicitly requested software-design guidance and local documentation tools with proportionate, clearly described access.

Choose the project root and output file deliberately: diagram generation reads all matching specification files beneath that root even with --scope. Use review or audit for read-only work and review changes from implementation modes. The bundled checks assess document structure, not runtime correctness; this assessment used static inspection.

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

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Output Handling: Unvalidated Output Injection, Cross-Context Output, Unbounded Output
• System Prompt Leakage: Direct Leakage, Indirect Extraction, Tool-Based Exfiltration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger

Findings (7)

Anti-Refusal Statement

High

• Category: Anti-Refusal
• Confidence: 90% confidence

Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · references/engineering/execution.md (reported line 13)May include surrounding context.

md

Repeated evaluation MUST neither duplicate a forbidden effect nor suppress a legitimate repeated action.
Ordinary calls, listeners, and Promise chains need the same guarantees.

For each reachable result, implement the declared response, retry, compensation, or intentional-ignore policy and state consequences.
Required responses MUST cover refusal and zero matches without omission, duplication, or delivery to another request.
Define candidate selection before choosing one or acting on all.
Later-valid query results need an explicit reevaluation trigger.

Anti-Refusal Statement

High

• Category: Anti-Refusal
• Confidence: 90% confidence

Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · references/guard/backfill.md (reported line 27)May include surrounding context.

md

Check all includes, signatures, and call arguments.
Preserve zero/many query behavior and request isolation.
Each reachable result needs its declared response/retry/compensation/ignore policy.
Loops terminate or continue under explicit control; a depth cap is optional.
Diagrams preserve conjunctions, multiple targets, and query reads.
Report rule count, scenario coverage, boundary findings, and unknowns.

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 · references/guard/map.md (reported line 15)May include surrounding context.

md

Omit `--output` to print Markdown to stdout.
`--check` requires `--output` and compares without writing.

Read [the map format](../map-format.md) for identity, resolution, and output rules.
Report output path or stdout, scope, exit status, and gaps.
A partial diagram may be written but MUST be marked partial.
With no specifications, existing output MUST remain unchanged.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read, network, shell.

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.

Shadow Command Trigger

Medium

• Category: Trigger Abuse
• Confidence: 70% confidence

Finding

Shadow Command Trigger: description clause 'Use only when explicitly invoked for software design, specifications, implementation, review, refactoring, or explanation with Daniel Jackson's concepts' conflicts with built-in command 'review'

Content

No source excerpt is available for this finding.

Generated section headings are forced to English without user opt-in.

Low

• Category: Output Handling
• Confidence: 96% confidence

Finding

The specification explicitly requires fixed English section headings in generated Markdown, regardless of the user's language preference. It provides neither a language choice nor a documented locale-specific justification.

Content

No source excerpt is available for this finding.

Scope Creep

Low

• Category: Excessive Agency
• Confidence: 70% confidence

Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · references/sources.md (reported line 38)May include surrounding context.

md

copies or substantial portions of the Software.

THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,