Back to skill

Security audit

transcribe.so

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a legitimate transcription skill, but users should review it because it relies on an unpinned global CLI and includes an optional watcher that can automatically upload local recordings to transcribe.so.

Install only if you trust the transcribe.so service and the current transcribe-so package publisher. Prefer a pinned or verified CLI version, keep the API key scoped with a low spend cap, and avoid enabling the heartbeat watcher unless it points to a dedicated folder that contains only recordings you intend to upload and transcribe.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:11
Finding

Unpinned Third-Party CLI Installation Creates a Supply-Chain Risk

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
80% confidence
Finding

The README instructs users to install the skill via npx skills add shsunmoonlee/transcribe-agent without pinning to an immutable version. If the upstream package/repository is later compromised or changed, users and agents may install altered code or skill instructions, creating a supply-chain attack path that is especially relevant because this skill can handle local files, remote URLs, and plugin/MCP integrations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The scheduled job watches a broad local folder and automatically transcribes anything new every 15 minutes, but the manifest does not define narrowing conditions, consent boundaries, or file-type/scope restrictions. In this context, that can cause accidental processing of sensitive recordings, including private meetings or calls, and automatic transmission to an external transcription service without an explicit per-run approval step.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This manifest sets up unattended scheduled processing of recordings but does not warn users that potentially sensitive audio/video placed in the watched directory will be automatically processed. Because the skill is specifically designed to handle recordings from local files and external sources, the missing warning materially increases the risk of inadvertent privacy, confidentiality, or compliance violations.

Content

No source excerpt is available for this finding.