to-questionnaire
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of Markdown-based instructions that guide an agent to interact with a user and produce a document. It does not contain any executable code, external network calls, or hardcoded credentials.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to populate a Markdown template, which is then saved to the local file system.
- Ingestion points: User inputs defining the recipient, purpose, and questions (SKILL.md).
- Boundary markers: None; user input is interpolated directly.
- Capability inventory: Limited to writing a
.mdfile to the current directory. - Sanitization: None provided for user-generated content.
- Assessment: Although a data ingestion surface exists, the risk is negligible as the skill lacks the ability to execute the generated file or transmit its contents externally.
Audit Metadata