sag
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONNO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access attempts were found. The skill operates within its stated purpose of providing a text-to-speech interface.
- [NO_CODE]: The skill does not include any scripts or executable files. It relies on a pre-installed 'sag' binary and environment configuration.
- [COMMAND_EXECUTION]: The skill facilitates the execution of the 'sag' utility via shell. This is the primary functionality for interfacing with the text-to-speech tool.
- [SAFE]: The skill correctly instructs that the API key (ELEVENLABS_API_KEY) should be provided via an environment variable rather than being hardcoded, which is a secure practice.
- [PROMPT_INJECTION]: Indirect prompt injection surface identified. 1. Ingestion points: User-provided text for synthesis (SKILL.md). 2. Boundary markers: Absent in shell command examples. 3. Capability inventory: Execution of 'sag' binary (SKILL.md). 4. Sanitization: Not specified in instructions. This risk is inherent to text-to-speech functionality.
Audit Metadata