Founder Story Brand Narrative

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 11:09 AM UTC
• Version: 0.1.1

Overview

This skill is a coherent founder-story copywriting helper with optional local scripts for briefs and linting, and I found no hidden persistence, credential access, network behavior, or destructive actions.

Installers should understand that this skill may guide an agent to run local Python helper scripts on user-provided copy files. Review generated marketing copy for factual accuracy because the skill explicitly uses placeholders rather than inventing facts, and avoid using the broad trigger terms for unrelated brand-copy tasks if founder narrative is not relevant.

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

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (5)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 97% confidence
• Finding: The declared description emphasizes creative writing assistance: creating and refining founder story, brand narrative, about-page/origin-story copy, and producing structured frameworks and polished copy aligned with DTC best practices. The actual code does not generate, rewrite, or refine copy. Instead, it parses markdown sections from a file, applies simple heuristic checks for section formatting, length, and generic phrases, and reports lint issues. While the subject matter overlaps founder-story-related marketing copy, the primary behavior is validation/linting, not content creation. That is a material description-behavior mismatch.

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 70% confidence
• Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The manifest description says to use the skill whenever the user mentions broad phrases like "brand voice," "mission/vision," or "landing page hero narrative," even if they do not say "founder story" explicitly. Those triggers overlap with many generic copywriting requests and may cause the skill to activate outside the narrower founder-story/artisan-brand context.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The prompts and expected outputs repeatedly require output "in English" and "professional DTC/independent-store terminology throughout," but there is no indication that the user is offered a language choice or that the locale restriction is justified as region-specific. Under the policy rule, forcing a specific language without opt-in is a natural-language policy violation.

Vague Triggers

Low

• Confidence: 79% confidence
• Finding: This is a JSON file, so SQP-1 applies. Multiple prompts and expected outputs require content to be produced "in English" or "Everything in English" without clarifying whether this is user-selected, optional, or limited to a justified region-specific context. The repeated broad language constraint is not tied to explicit scope or exclusions, making the invocation expectations less specific in this manifest-like file.

Static analysis

No suspicious patterns detected.