Security audit

PrototypeSkill

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed markdown workflow skill for generating a prototype document from an existing PRD, with limited project-file writes and no hidden code, network use, persistence, or credential access.

Before installing, users should understand that this skill writes a requirements/prototype.md file and may automatically continue the SDLC workflow through using-aisdlc after that file is created. It is best suited to teams that intentionally use this Chinese-language, ASCII-wireframe SDLC process.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill explicitly instructs the agent to write prototype.md and then immediately invoke using-aisdlc to continue execution without waiting for user confirmation. This creates an autonomy boundary issue: the agent may perform filesystem modifications and trigger additional workflow steps the user did not explicitly approve in the current turn, which can lead to unintended changes or cascading actions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This markdown template is written entirely in Chinese and gives prescriptive instructions for producing the document in that language, but it does not offer an opt-in language choice or state that the skill is intentionally limited to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: The instruction says user preference cannot override the constraint and requires ASCII wireframes even if the user dislikes them. While this is framed as a portability requirement rather than regional locale, it still imposes a presentation-language/script constraint without offering user choice or clearly documenting an opt-in.
Content: No source excerpt is available for this finding.