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 in SKILL.md is 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
Risk Level
SAFE
Analyzed
Jun 16, 2026, 12:57 AM
Security Audit — agent-trust-hub — survey-analyzer