Back to skill

Security audit

rd-workflow食品研发流程指引

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language R&D workflow guide made of Markdown templates, with no executable code, persistence, credential handling, or hidden behavior found.

Install this if you want Chinese-language product R&D process checklists and stage guidance. Be aware it may activate for broad workflow questions, and regulatory or standards-related suggestions should be verified against current authoritative sources before business use.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The description says the skill should be used for '产品研发项目或需要流程指导时', which is broad enough to match many ordinary conversations about work or planning. Overly permissive activation boundaries increase the chance of accidental invocation and irrelevant procedural influence, even though the skill does not contain overtly malicious behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger condition includes vague situations such as '阶段转换、流程不清晰时', which are common and nonspecific. This can cause the skill to activate too broadly, leading to unintended workflow steering in contexts where the user did not explicitly request this guidance, but the content itself is procedural and not directly harmful.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown template is entirely written in Chinese and provides no indication that language selection is optional or tied to a China-specific or Chinese-speaking workflow. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.