voice-matching-wizard
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves analyzing user-provided writing samples, which creates an attack surface where malicious instructions embedded in the input text could attempt to subvert the agent's instructions.
- Ingestion points: Writing samples provided by the user in Phase 1 of
SKILL.mdand during the interactive prompts inWIZARD.md. - Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore any potential instructions found within the text being analyzed.
- Capability inventory: The skill is limited to generating Markdown text and does not have the capability to execute shell commands, access the network, or modify system files.
- Sanitization: Absent; no input filtering or sanitization is performed on the user-provided text.
- [NO_CODE]: The skill is comprised purely of documentation and templates and contains no scripts, binaries, or automated configuration files.
Audit Metadata