Back to skill

Security audit

Transcript Dock

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners found no AIG issues and describe a skill that uses an API key, while flagging a possible external transmission and a missing privacy notice before media upload.

Before installing, consider whether you are comfortable using an API key and sending media to Transcript Dock for processing. The scan found no AIG issues, but Skillspector's analysis was partial because a local reference could not be resolved, so the evidence is incomplete.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 11)May include surrounding context.

md
env:
        - TRANSCRIPTDOCK_API_KEY
      bins:
        - curl
    primaryEnv: TRANSCRIPTDOCK_API_KEY
    envVars:
      - name: TRANSCRIPTDOCK_API_KEY

The media-upload workflow lacks a user-facing privacy warning.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The workflow instructs the agent to upload user-owned media to Transcript Dock without telling the user that the file's contents will leave their workspace and be processed by a third-party service. Ownership of a file does not establish informed consent to disclose potentially private audio or video.

Content

No source excerpt is available for this finding.