ClawHub
Back to skill

Security audit

Community Outreach

Security checks for vulnerabilities and agentic risk

Overview

This skill is a transparent community-outreach helper that searches public communities, drafts responses, and writes a local outreach plan without evidence of hidden or harmful behavior.

Installers should expect the skill to read project documentation, search public web/community sources, and create a local docs/outreach-plan.md file. Review drafts before posting and check for an existing outreach plan if overwrite risk matters.

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

Low
Confidence
95% confidence
Finding
The skill instructs the agent to write `docs/outreach-plan.md` into the workspace without first explicitly warning the user that it will modify local files or obtaining confirmation. While the content is benign and expected for this marketing workflow, silent file creation can still surprise users, overwrite existing planning documents, or be chained with other behaviors that normalize unannounced workspace changes.

Static analysis

No suspicious patterns detected.