listenhub-tts
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches audio files and speaker metadata from the ListenHub API at
api.marswave.ai. This is the core functionality of the skill. - [COMMAND_EXECUTION]: Uses the
Bashtool to executecurlcommands for sending synthesis requests to the API and downloading binary audio data to the local environment. - [PROMPT_INJECTION]: The skill ingests untrusted text from local files or remote URLs, creating a surface for indirect prompt injection.
- Ingestion points: Ingests content using the
Readtool for files likearticle.mdor via thecontentUrlparameter in long-text mode. - Boundary markers: The skill lacks explicit delimiters or instructions to the agent to isolate the ingested text from its own behavioral instructions.
- Capability inventory: The skill possesses the capability to execute network requests (
Bash/curl), read files (Read), and write files (Write). - Sanitization: No sanitization or validation is applied to the external text content before it is processed by the synthesis workflow.
Audit Metadata