listenhub-tts
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary text from user input, local files, and external URLs. * Ingestion points: Reads local files (e.g., article.md) and fetches content from user-specified URLs. * Boundary markers: The instructions lack delimiters to isolate external text from agent instructions. * Capability inventory: Uses Bash for curl requests and Write for saving files. * Sanitization: No sanitization logic is specified for ingested content.
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute curl commands for API interaction with api.marswave.ai.
- [DATA_EXFILTRATION]: The skill performs network operations (via curl) to the non-whitelisted domain api.marswave.ai. While these are for API communication, it involves sending user-supplied content to a remote server.
Audit Metadata