Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 90% confidence
- Finding
- The skill documentation describes capabilities that read local files (script.json), write output audio files and a manifest, likely use environment variables for API credentials, and make network calls to an external TTS service, yet no permissions are declared. This creates a trust and enforcement gap: a user or platform may authorize or review the skill under the false assumption that it has no sensitive capabilities, increasing the risk of unintended data access, exfiltration, or unexpected external API usage.
