feedback
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto download and run@spotify/portal-cli. This package is a Spotify-owned resource and the tool invocation is the primary functionality of the skill.- [COMMAND_EXECUTION]: The skill executes a shell commandnpx @spotify/portal-cli actions telemetry:submit-feedback --text "<feedback>". The<feedback>placeholder is populated with user-supplied text, which could lead to command injection if the input is not properly handled by the execution environment.- [INDIRECT_PROMPT_INJECTION]: - Ingestion points: The skill accepts arbitrary text from the user to be used as feedback (SKILL.md).
- Boundary markers: Instructions require the agent to "Show the exact text that will be sent and ask before invoking the action."
- Capability inventory: Subprocess execution via
npxshell command (SKILL.md). - Sanitization: Instructions explicitly forbid including secrets, tokens, or personal data and require asking the user to rephrase if such data is detected.
Audit Metadata