ClawHub
Back to skill

Security audit

Pipeline

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed pipeline coordinator that automates other skills after confirmation, with limited local state and no bundled executable payload.

Install only if you want a skill that can coordinate multi-step research or development workflows. Before running it, confirm the listed stages are the ones you expect, be aware it may create .solo pipeline state and log files, and treat deletion of the state file as an irreversible cancel for that pipeline run.

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
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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 (2)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · SKILL.md (reported line 159)May include surrounding context.

md
1. **Always confirm** before starting a pipeline.
2. **Don't skip stages** — the hook handles progression.
3. **Cancel = delete state file** — tell users this if they want to stop.
4. **Max iterations** prevent infinite loops (default 5 for research, 15 for dev).
5. **Use `--no-dashboard`** when running from within Claude Code skill context.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill instructs users to cancel a pipeline by deleting the state file, which is a destructive action affecting pipeline continuity and recovery state. While the document explains the mechanism, it does not explicitly warn that deletion may stop recovery/resume behavior or disrupt an in-progress pipeline.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.