ClawHub
Back to skill

Security audit

Outreach

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only outreach guidance skill with no executable code, network calls, credential handling, or hidden unsafe behavior found.

Installers should treat this as a writing and campaign-planning aid. Use it with care for privacy, consent, and anti-spam compliance when handling contact lists or sending outreach, but the artifact itself does not automate sending or access private accounts.

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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • 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)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: Outreach
description: Plan, personalize, and track outreach campaigns for sales, PR, recruiting, partnerships, and link building with timing strategy and follow-up cadence.
---

## Situation Detection

| Context | Load |
|---------|------|
| Writing cold emails, follow-ups, subject lines | `templates.md` |
| Sales outreach (SDR, BDR, AE) | `by-type.md` → Sales section |
| PR/Media pitching, influencer outreach | `by-type.md` → PR section |
| Link building, guest posts, SEO outreach | `by-type.md` → SEO section |
| Recruiting, talent sourcing | `by-type.md` → Recruiting section |
| Investor, par

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

md
*Build over time. Update after campaigns.*

### What Works
<!-- "Subject line: Question format +40% opens" "Tuesday 10am best time" -->

### What Fails
<!-- "Long emails ignored" "LinkedIn connect requests <10% accept" -->

Static analysis

No suspicious patterns detected.