ClawHub
Back to skill

Security audit

Handmade Editorial Poster

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed photo-to-poster image-generation workflow with no hidden code, persistence, or unrelated data access.

Install only if you are comfortable sending the selected photos to whatever image-generation tool or provider your agent is configured to use. Avoid including sensitive photos unless that provider's privacy and retention settings are acceptable to you.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Line L30 instructs the skill to "Deliver one ready-to-paste English prompt per source photo," which imposes a specific language choice regardless of the user's language preference. This is a natural-language locale policy issue because the file does not offer an alternative language option or require user opt-in.

Content

No source excerpt is available for this finding.

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/platform-adapters.md (reported line 3)May include surrounding context.

md
# Platform adapters

This skill is provider-neutral. The artistic contract stays unchanged; only the handoff mechanism differs. Do not claim a named platform supports image generation without checking its active model/tool configuration.

## Capability-first adapter

Static analysis

No suspicious patterns detected.