actions

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the @spotify/portal-cli tool to perform discovery and execution of platform actions. It explicitly instructs the agent to use --dry-run for previews and to obtain user consent before running any commands that modify state.\n- [EXTERNAL_DOWNLOADS]: Downloads the @spotify/portal-cli package from the npm registry using npx. This is an official scoped package belonging to the skill's authoring organization.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface where user-provided identifiers and JSON payloads are interpolated into shell commands. \n
  • Ingestion points: User-provided values for <action-id> and <json> in SKILL.md. \n
  • Boundary markers: The skill suggests wrapping JSON input in single quotes (--input '<json>'). \n
  • Capability inventory: Shell command execution via npx in SKILL.md. \n
  • Sanitization: The instructions require the agent to display the exact command for user review and authorization prior to execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 12:37 AM
Security Audit — agent-trust-hub — actions