Security audit
PDF Toolbox
Security checks for vulnerabilities and agentic risk
Overview
The skill performs the advertised PDF operations locally, preserves source files, and shows no hidden uploads or unrelated access.
Install dependencies in a dedicated Python environment and use reviewed versions for reproducibility. Check output previews before relying on transformed documents, and remove saved exports when no longer needed.
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 findings are pending for this release.