ClawHub
Back to skill

Security audit

Auto Dev Pipeline

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed automation pipeline that creates app requirements, code, and tests through sub-agents, with no evidence of hidden execution, credential access, exfiltration, or destructive behavior.

Install this only if you want an agent to run a hands-off PRD-to-code-to-tests workflow. Expect generated files and directories, downstream skill usage, and possible runtime cost; review outputs before using generated code in a real project.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (4)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 211)May include surrounding context.

md
### For Pipeline Maintenance
1. **Monitor Performance**: Track execution times and success rates
2. **Update Skills**: Keep prd/dev/qa skills current with best practices
3. **Collect Metrics**: Measure code quality and user satisfaction
4. **Iterate Improvements**: Continuously enhance automation logic

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises a 'hands-off' automated workflow but does not clearly warn that it will create multiple files and directories across several pipeline stages. This reduces informed user consent and increases the chance of unexpected workspace modification, especially because the pipeline coordinates other skills and persists outputs automatically.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger mechanism is broad enough to activate on generic app-idea requests, which can cause the skill to launch a multi-stage automation pipeline without an explicit user opt-in checkpoint. In this context, that means unintended sub-agent execution, file creation, and resource consumption may occur from ordinary conversation text rather than a clearly bounded command.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The documented trigger examples are all in Chinese, and no nearby text states that other languages are supported or that Chinese is required for a justified regional reason. This can be read as a locale preference baked into the skill without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.