skills/obra/muse-skills/spotify/Gen Agent Trust Hub

spotify

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill interacts with the Spotify service by executing two specialized CLI tools: spotify-api and save-to-spotify. These tools are used for OAuth session management, catalog searching, and library modification. The instructions specify using these tools directly from the system PATH.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external metadata and messages from Spotify's APIs, which creates a surface for indirect prompt injection if those sources contain malicious instructions.
  • Ingestion points: External data enters the agent context through the outputs of spotify-api search, spotify-api library, spotify-api experience, and save-to-spotify inventory commands as documented in SKILL.md.
  • Boundary markers: The instructions do not define explicit delimiters or 'ignore embedded instructions' warnings when the agent interpolates external strings like track titles or fallback messages into its responses.
  • Capability inventory: As defined in manifest.yaml and SKILL.md, the skill has capabilities to modify the user's library, manage playlists, control playback, and delete shows or episodes.
  • Sanitization: While the skill is directed to use JSON mode for data parsing and to extract only relevant fields, there is no mention of sanitization or escaping for the external strings before they are presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 11:45 PM