edge-tts

Warn

Audited by Snyk on Nov 22, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The required workflow converts "the target text (message, search results, summary)" to audio (SKILL.md Workflow step 3), so the agent may pass arbitrary web search results, which outsiders can publish but cannot force into the workflow, to the TTS tool; no monitored inbox or feed is read.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (medium risk: 0.30). The decisive boundary is the setup path in DISTRIBUTION.md, which instructs git clone https://github.com/clawdbot/edge-tts-skill.git to fetch installable skill material; the publisher matches the declared author "Clawdbot," but there is no pinned digest or signature, so it is classed as common/reputable rather than strongly authenticated first-party provenance (medium). The npm package names and the tts.travisvn.com voice-testing link are not operational dependencies.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill's only state-changing operations are local preference writes to ~/.tts-config.json (including a reset that deletes it), which are recoverable by regenerating defaults and lack explicit irreversible operational loss, so the tier is low.

Issues (3)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 22, 2026, 01:12 AM
Issues
3