setup

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to execute CLI commands and process the resulting JSON output, specifically from @spotify/portal-cli actions list --json. This creates a vulnerability surface where a compromised or malicious Portal backend could return instructions that influence the agent's subsequent actions.
  • Ingestion points: Output of @spotify/portal-cli commands (SKILL.md).
  • Boundary markers: None present; instructions emphasize JSON consumption without specifying delimiters or ignore-instructions warnings.
  • Capability inventory: Shell command execution, network access via the CLI tool, and file system interaction through the setup process.
  • Sanitization: No explicit validation or sanitization is required for the tool output before agent processing.
  • [COMMAND_EXECUTION]: The skill relies on shell command execution via npx to interact with the @spotify/portal-cli and verify the local environment (node, npm).
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch the @spotify/portal-cli package from the public npm registry during the setup workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 12:38 AM
Security Audit — agent-trust-hub — setup