voice-extraction
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted user-provided text and interpolates it directly into subagent prompts without sanitization.
- Ingestion points: The
[FULL PASTED CONTENT]variable within the subagent prompt template inSKILL.md. - Boundary markers: Absent. The content is inserted directly into the prompt without using delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill uses the
Agenttool to launch 10 parallel subagents and writes the synthesized output to the local file system (e.g.,brand/voices/[name].md). - Sanitization: Absent. There is no evidence of filtering or validation of the input text before it is processed by the subagents.
Audit Metadata