controlling-spotify

Fail

Audited by Gen Agent Trust Hub on Oct 13, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The installation script scripts/install-mcp-server.sh clones a third-party repository (github.com/marcelmarais/spotify-mcp-server.git) that does not belong to a verified organization.
  • [REMOTE_CODE_EXECUTION]: Installation involves running npm install and npm run build on the cloned external repository, followed by executing the resulting build output (build/index.js).
  • [DYNAMIC_EXECUTION]: The script scripts/apply-patch.js performs runtime modification of the downloaded source code by injecting logic into src/utils.ts before the build process, facilitating the execution of modified code.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Spotify API which could contain malicious instructions.
  • Ingestion points: searchSpotify, getNowPlaying, and getPlaylistTracks tools in SKILL.md ingest external track names, artist bios, and descriptions.
  • Boundary markers: No explicit delimiters or instructions are used to separate external data from agent instructions.
  • Capability inventory: The skill has the ability to execute shell commands (bash, node, npm) and perform network operations via the Spotify API.
  • Sanitization: No evidence of output sanitization or validation of the data retrieved from the Spotify API was found.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Oct 13, 2026, 06:49 PM