to-questionnaire
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's instructions and configuration do not exhibit malicious patterns like prompt injection, exfiltration, or obfuscation.
- [COMMAND_EXECUTION]: The skill directs the agent to save questionnaire content as a local file. This operation is limited to the current working directory and is consistent with the primary purpose of the skill.
- [PROMPT_INJECTION]: The skill processes user input to populate a document template, which defines a surface for indirect prompt injection.
- Ingestion points: User responses gathered during the information discovery process described in Step 1 and Step 2 of SKILL.md.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the generated Markdown file.
- Capability inventory: The agent is instructed to write the resulting content to a local file in the current directory.
- Sanitization: There are no instructions to sanitize or filter user-provided content before it is placed into the document template.
Audit Metadata