Security audit
shumianyu
Security checks for vulnerabilities and agentic risk
Overview
This skill is a plain text workflow for turning completed ASR transcripts into polished written text, with no hidden execution or data-access behavior found.
This appears safe to install as a transcript-cleanup workflow. Because ASR transcripts can contain sensitive meeting or interview content, users should ensure any implementation clearly controls when buffering ends, whether transcripts are retained, and which translation or rewriting service processes the text.
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
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.