ClawHub
Back to skill

Security audit

Reciprocity

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only coaching skill about recognizing and ethically handling reciprocity pressure, with some dual-use persuasion examples but no hidden execution, persistence, or data access.

Install only if you want a decision-making aid for spotting and reasoning about reciprocity pressure. Use the sender-side material ethically: do not use gifts, free samples, or concessions to pressure people into choices they would reject on the merits, and follow bright-line rules in regulated contexts.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This content gives concrete, operational guidance for using reciprocity to induce compliance, including statements like 'you can extract compliance' and examples of commercial exploitation, without a prominent ethical warning or strict framing around defense-only use. Although it includes some defensive advice later, the surrounding language still normalizes and teaches a manipulative influence tactic that could be misused in sales, fundraising, or interpersonal contexts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.