ClawHub
Back to skill

Security audit

Photoshop

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent Photoshop automation, but it delegates control to unaudited local Flue instructions and recommends running an unpinned external setup command.

Review Flue and its installed adapter docs before use, prefer a pinned and verified install in a constrained environment, and only approve setup or Photoshop-changing actions that match your current task.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:15
Finding

Unpinned Third-Party Package Installation Followed by Setup Execution

Content
View full analysis
Remediation
View remediation
" ``` 2. Require installation from a lock file or artifact with a verified SHA-256 hash. 3. Use `--require-hashes` where practical and document the expected package index explicitly. 4. Separate package installation from `flue setup` so the resolved package and setup behavior can be inspected before execution. 5. Display the package name, exact version, source, integrity hash, and expected setup changes when requesting approval. 6. Prefer a dedicated virtual environment and run setup with the least-privileged user account needed for application automation. 7. Review package metadata, dependencies, setup behavior, and adapter scripts before endorsing a release. 8. Do not use elevated privileges unless a separately documented and narrowly scoped operation genuinely requires them. ]]>

T01 · Skill Instruction Hijacking

Warning
Location
SKILL.md:14
Finding

Operational Authority Delegated to Mutable External Instruction Files

Content
View full analysis
Remediation
View remediation

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

Static analysis

No suspicious patterns detected.