Spotify Automation
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface through the interpolation of external data into sensitive tool operations.\n
- Ingestion points: The skill utilizes template variables such as
{{playlist_name}},{{description}}, and{{date}}withinSKILL.mdand acceptsSearch queriesas input for discovery workflows.\n - Boundary markers: No specific boundary markers or system instructions are defined to separate untrusted user/data input from the agent's executable instructions or to prevent the agent from obeying commands embedded in that data.\n
- Capability inventory: The skill utilizes high-privilege tools including
spotify_playback(controlling audio output) andspotify_playlist(modifying user data), which increase the potential impact of an injection attack.\n - Sanitization: No sanitization, validation, or escaping logic is described in the
SKILL.mdfile for the processing of external content.
Audit Metadata