buildbetter-survey-research

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze data from external survey respondents, which constitutes untrusted input.\n
  • Ingestion points: Survey data is fetched using the list-survey-responses and get-survey-response tools (referenced in SKILL.md).\n
  • Boundary markers: While the skill instructs the agent to separate answer evidence from analysis, it lacks explicit technical boundary markers or delimiters (such as XML tags or triple backticks) to strictly isolate untrusted content from the agent's instruction context.\n
  • Capability inventory: The skill possesses significant capabilities, including create-survey, update-survey, schedule-survey, and send-survey-test-email, which could be targeted by instructions hidden in survey responses.\n
  • Sanitization: The instructions do not specify any sanitization, escaping, or filtering of respondent content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 09:33 AM