survey-question-designer
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests and processes untrusted user data to generate survey questions and structures.\n
- Ingestion points: User-provided arguments for 'survey goal', 'audience', and 'channel' defined in
SKILL.md.\n - Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to ignore instructions that may be embedded within the user data.\n
- Capability inventory: The skill specifies the use of
ReadandWritetools inSKILL.md. No executable scripts or subprocess capabilities are present.\n - Sanitization: Absent. There is no logic provided to sanitize, escape, or validate the user-supplied content before it is processed by the agent.\n- [NO_CODE]: The skill distribution consists entirely of Markdown documentation and JSON configuration files. No Python, JavaScript, shell scripts, or other executable files are included.\n- [SAFE]: The skill includes links to
infloq.comfor supplemental survey examples. This domain corresponds to the author's homepage and repository listed in the plugin metadata and is used for legitimate reference purposes related to the skill's primary function.
Audit Metadata