ssml
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a developer-focused utility for generating SSML (Speech Synthesis Markup Language). It provides structural guidance and templates for creating valid XML documents.
- [PROMPT_INJECTION]: Although the skill processes untrusted user input to generate SSML, it mitigates potential risks (such as XML injection or indirect prompt injection) by explicitly instructing the agent to escape XML special characters (e.g., &, <, >) and quote all attribute values. It contains no instructions to override agent safety protocols.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns, subprocess calls, or dynamic code evaluation (like eval or exec) were detected in the skill instructions or reference files.
- [DATA_EXFILTRATION]: The skill does not access sensitive local files, environment variables, or credentials. It does not perform network operations to non-whitelisted domains. While it mentions the use of external custom lexicons via URI, it provides only a standard placeholder example (example.com).
- [COMMAND_EXECUTION]: The skill does not use any shell command execution or dynamic context injection patterns (!command) that could lead to unauthorized system access.
Audit Metadata