survey-analyzer
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of natural language instructions and a prompt template. It does not include any scripts, dependencies, or configuration files that could execute commands on the system.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted external data (survey responses).
- Ingestion points: The
[PASTE SURVEY RESPONSES]variable inSKILL.mdis used to interpolate user data directly into the LLM prompt. - Boundary markers: The prompt template uses
<survey_data>XML tags to attempt to separate data from instructions. - Capability inventory: The skill has no capabilities (no file system access, no network operations, and no subprocess execution).
- Sanitization: No sanitization or filtering is applied to the input responses. Because the skill lacks any system-level or network capabilities, the risk associated with this surface is negligible.
Audit Metadata