ClawHub
Back to skill

Security audit

Content Amplifier

Security checks for vulnerabilities and agentic risk

Overview

This marketing planning skill is coherent and disclosed; it creates content and ad-budget recommendations but does not install code or automatically spend money.

Before installing, be aware that this skill can help plan paid ad spend and may use sensitive marketing inputs such as creator metrics, rights terms, CRM audiences, and ad-platform performance if you opt into connectors. Confirm rights and budget assumptions before acting on its recommendations, and only approve memory saves for information you are comfortable reusing later.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 155)May include surrounding context.

md
- [content-amplifier --mode paid](SKILL.md) — when repurposed ad variations are ready for paid spend (run only if repurpose ran this session and paid has not).

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 146)May include surrounding context.

md
## Save Results

After delivering findings, ask: "Save these results for future sessions?" If yes, write `memory/influencer/content-amplifier/YYYY-MM-DD-<topic>.md` with: one-line verdict/headline, top 3-5 actionable items, open loops or blockers, and source data references. Only the auditor-class gates may write memory without asking — this skill asks first, and hands veto-like risks (missing disclosure, unsubstantiated claims) to [creator-content-auditor](../creator-content-auditor/SKILL.md) rather than judging them here.

## Next Best Skill

Static analysis

No suspicious patterns detected.