ClawHub
Back to skill

Security audit

Offer Engine

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill is a bounded offer-drafting workflow that repeatedly requires evidence, authorization checks, and explicit approval before any external action.

Before installing, users should understand that this skill can help draft business offer materials from provided evidence and may stage external actions, but it requires exact approval before anything buyer-facing, financial, contractual, or account-changing is performed.

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

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 21)May include surrounding context.

md
Require `Run Authorization`, the current `Money Machine Run`, `Revenue Profile`,
`Experiment Brief`, and `Opportunity Evidence Table` with its claim ledger.
Run Authorization permits private offer analysis, drafting, and artifact
creation for the named route without asking for another approval. If an input
is absent or the route materially changed, return to `moneyprinter` or
`opportunity-radar`; do not create a new route silently. Run Authorization never
permits outreach, publication, payment acceptance, contracting, account

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 · references/offer-brief.md (reported line 45)May include surrounding context.

md
**Example offer:** an approved content-to-offer measurement pack: a content
inventory, disclosed call-to-action variants, and a tracking worksheet.
Exclude undisclosed endorsements, fake scarcity, fabricated testimonials,
platform-policy violations, guaranteed conversion, and posting without
approval. The smallest payable version is one approved content batch analysis
and draft package, with results labeled as Pipeline signal or Simulation as
appropriate.

Static analysis

No suspicious patterns detected.