ClawHub
Back to skill

Security audit

Social Growth Ops

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent social-content planning and scheduling-handoff guide with explicit anti-spam and user-confirmation limits.

Review generated posts before approval, provide credentials only to your own scheduling system outside the skill, and use the explicit CONFIRM SOCIAL POST flow only when the exact platforms, text, and timing are correct.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
70% confidence
Finding

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Content

Scanner excerpt · SKILL.md (reported line 100)May include surrounding context.

md
## Output Format

Always respond with the following sections:

1. `## Proposed Plan`
2. `## Draft Pack`

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill's brand voice inputs restrict the language field to 'RU/EN/mixed', which imposes a locale/language limitation in the skill instructions. This is a natural-language policy concern because the constraint is not presented as optional, nor is it justified as region-specific or user-selected beyond those listed options.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.