Strategy Interview

• Outcome: Review
• Latest audit: Sep 16, 2026 · 5:34 AM UTC
• Version: 1.0.4

Overview

This is a coherent strategy-interview skill, but it may persist sensitive interview notes before clearly asking the user for permission.

Install only if you are comfortable with the agent creating local strategy notes during longer interviews. For confidential strategy, personnel, competitive, or career discussions, ask the agent to use chat-only mode or to request confirmation before writing `.beagle` state or final markdown files.

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
• System Prompt Leakage: Direct Leakage, Indirect Extraction, Tool-Based Exfiltration
• Memory Poisoning: Persistent Context Injection, Context Window Stuffing, Memory Manipulation
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger

Findings (13)

Memory Manipulation

High

• Category: Memory Poisoning
• Confidence: 80% confidence

Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md

**The four hallmarks of bad strategy** (watch for these constantly):
- **Fluff** — abstract, buzzword-heavy language that sounds sophisticated but says nothing.
- **Failure to face the challenge** — no clear statement of what the actual problem is.
- **Mistaking goals for strategy** — "grow revenue 30%" is a goal. Strategy is *how*, and more importantly *why that how*.
- **Bad strategic objectives** — either a laundry list with no priority, or blue-sky objectives that restate the problem as if wishing made it so.

Anti-Refusal Statement

High

• Category: Anti-Refusal
• Confidence: 85% confidence

Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 188)May include surrounding context.

md

## Style and posture

- **Interview, don't lecture.** The user knows their situation; you know the framework. Ask the questions the framework demands.
- **One or two questions per turn.** Walls of questions get walls of shallow answers.
- **Quote the user's own words back** when formalizing the kernel — builds trust and catches misinterpretation early.
- **Don't name-drop frameworks or sources.** The framework shows up in what you ask, not in citations.

Anti-Refusal Statement

High

• Category: Anti-Refusal
• Confidence: 85% confidence

Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · references/blue-ocean.md (reported line 118)May include surrounding context.

md

## Posture when introducing this lens

Don't lecture about value innovation theory. Use the interview prompts above to let the user discover the pattern themselves. If they describe 5 factors where everyone converges, reflect it back: "So on the dimensions your industry competes on, you and the top competitors are roughly similar. What's that tell you about the value of investing more in those same dimensions?"

If the user engages with it, run the four actions and noncustomer prompts. If they resist — "no, we just need to execute better on what we have" — note it in `strategy-notes.md` as an open question and move on. They may be right. They may also not be ready to hear it yet. Either way, forcing it helps nobody.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 87% confidence

Finding

The manifest description uses very broad trigger phrases like direction-setting, prioritization struggles, and strategy planning, which can cause the skill to activate for ordinary advisory conversations that do not require this workflow. Over-broad routing increases the chance that the agent applies a heavy, file-writing, stateful interview process in contexts the user did not intend, creating privacy and consent risks indirectly.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The skill permits in-progress writes under .beagle/strategy/<subject-slug>/ at any point during the interview, before any explicit user consent for intermediate persistence. This creates a durable-recording behavior that could store sensitive business, personnel, or career information without the user's informed approval.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

This section explicitly instructs the agent to create a durable interview-state directory and maintain multiple state files based on conversation length or complexity, but it does not require prior disclosure or consent from the user. Because strategy interviews often contain confidential operational, competitive, and stakeholder information, silent persistence meaningfully raises confidentiality and data-retention risk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

The file instructs the skill to write to strategy-notes.md, which expands behavior beyond the declared guided-conversation scope into persistent artifact creation. That can create unauthorized state changes, unexpected data retention, or document modification behavior that users and the manifest did not clearly consent to.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium

• Category: Not specified by scanner
• Confidence: 84% confidence

Finding

The skill metadata says this skill should not review existing strategy documents, but the reference text tells the agent to record disagreements in strategy-notes.md and optimize for 'a better document at the end.' This creates a scope mismatch that can lead the agent to generate or update strategic documentation despite the advertised limitation, undermining user expectations and control.

Content

No source excerpt is available for this finding.

Indirect Prompt Extraction

Medium

• Category: System Prompt Leakage
• Confidence: 70% confidence

Finding

Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.

Content

Scanner excerpt · references/kernel.md (reported line 22)May include surrounding context.

md

- Long lists of challenges with no weighting. A good diagnosis picks.

**Interview prompts to sharpen a diagnosis:**
- "If you had to describe this situation to a smart outsider in three sentences, what would you say?"
- "What is the *one* thing that, if it were different, would change everything?"
- "What are people inside the org afraid to say out loud about this?"
- "Is there an analogy — another company, another industry, a historical moment — that this reminds you of?"

Description-Behavior Mismatch

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The manifest explicitly says this skill should not review existing strategy documents and that such work belongs to a different skill. However, this reference guide includes a dedicated workflow for 'using the cascade on an existing strategy' and instructs how to analyze an existing strategy and integrate findings into notes and draft outputs. That is a semantic scope mismatch between stated skill purpose and documented behavior.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 80% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/wardley-mapping.md (reported line 59)May include surrounding context.

md

### Extracting the value chain through conversation

Don't ask the user to "draw a map." Instead, ask questions that surface the chain and where things sit on the evolution axis.

**Start from the user need and work down:**

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The template explicitly instructs the agent to write strategy-draft.md and strategy-notes.md into the user's current working directory without requiring a fresh, explicit confirmation at the time of file creation. This creates a real integrity-risk pattern: an agent could modify the filesystem based on ambiguous user intent, and in long conversations the user may not realize files will be created automatically.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 84% confidence

Finding

The pressure-test scenarios instruct the agent to create or update files such as strategy-notes.md, .beagle/.../state.md, composition.md, and strategy-draft.md without indicating that the user should be notified or asked for consent before filesystem changes. In an agent skill, implicit writes can surprise users, overwrite existing work, or persist sensitive conversation content in project files, especially because these scenarios normalize file creation as expected behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.