grill-me-with-spec

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 8:58 PM UTC
• Version: 1.0.3

Overview

This skill is a Portuguese-first requirements interview and SPEC-writing workflow with no executable code or hidden install behavior found.

Install this if you want a pt-BR requirements interview that writes a local SPEC before implementation. Be aware it will push the agent to inspect repository context and create/update .specs files; confirm the language and review the SPEC carefully before approving it.

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

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Natural-Language Policy Violations

Medium

• Confidence: 98% confidence
• Finding: The skill mandates that all user-facing interaction be in Portuguese without checking the user's language preference or obtaining consent. This can undermine user comprehension of requirements and approvals, increasing the risk of misunderstandings in a specification workflow where precise agreement is critical.

Autonomous Decision Making

Medium

• Category: Excessive Agency

Content

1. **No guessing.** If a fact is missing, ask the user. If the user declines, mark it `[A DEFINIR]` in the SPEC.
2. **No implementation.** Never write implementation code. The output is the SPEC only.
3. **Shared understanding first.** The session ends only when the design-tree frontier is empty.
4. **Evidence-based.** Look up repository, docs, and code facts with sub-agents. Do not ask the user for things you can find yourself.

## The Design Tree

• 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.

Autonomous Decision Making

Medium

• Category: Excessive Agency

Content

1. **No guessing.** If a fact is missing, ask the user. If the user declines, mark it `[A DEFINIR]` in the SPEC.
2. **No implementation.** Never write implementation code. The output is the SPEC only.
3. **Shared understanding first.** The session ends only when the design-tree frontier is empty.
4. **Evidence-based.** Look up repository, docs, and code facts with sub-agents. Do not ask the user for things you can find yourself.

## The Design Tree

• 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.

Natural-Language Policy Violations

Low

• Confidence: 91% confidence
• Finding: The template instructs writers to express BDD criteria as either English or pt-BR, explicitly naming a specific locale in the guidance. Because the file is a general-purpose template and does not state that Portuguese is optional based on user preference or limited to a region-specific context, it can encourage locale-specific output without clear opt-in.

Scope Creep

Low

• Category: Excessive Agency

Content

- **Registries:** use only approved corporate/organization registries — never public registries unless explicitly authorized.
- **API headers:** use the organization's standard correlation / authentication headers as defined by the API governance team.
- **Security:** do not log PII/tokens/identifiers; store secrets via the organization's secret manager; no `.env` in commit.
- **Scope:** do not invent requirements or expand scope. Stop and ask on ambiguity.
- **Architecture:** no business logic in controllers/components; domain does not access infrastructure.

## 9. Definition of Done

• Confidence: 75% 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.

Static analysis

No suspicious patterns detected.