ClawHub
Back to skill

Security audit

Feedback Loops

Security checks for vulnerabilities and agentic risk

Overview

This is a plain markdown thinking skill for analyzing feedback loops, with no code execution, credential access, persistence, or hidden system changes.

Installers should treat this as a reasoning aid, not an automated decision system. Its recommendations may influence business or operational planning, so users should verify assumptions, data quality, and intervention consequences before acting.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md
## Coaching Novices (Adaptive Front Door)

- **Engine mode:** concrete case → run The Process directly.
- **Coach mode:** unfamiliar or no concrete case → guide, don't lecture.

In Coach mode, respond one step at a time. Each [WAIT] is a hard stop — output only that step's question, then stop.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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.

Content

Scanner excerpt · SKILL.md (reported line 102)May include surrounding context.

md
## Red Flags

- Trends extrapolated in a feedback-driven system · Oscillation blamed on external variability without checking internal loop generators · Intervention at parameter level when loop structure is the source · "Be more careful" proposed in a Forrester-adversarial structure · Stocks and flows confused · Death spiral or growth narrative with no loop/nodes/delays specified · All interventions at lowest (parameter) leverage level

## Verification

Static analysis

No suspicious patterns detected.