buildbetter-survey-research
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze survey responses, which constitute untrusted data from external sources.
- Ingestion points: The workflow incorporates the
list-survey-responsesandget-survey-responsetools to retrieve participant data into the agent's context in SKILL.md. - Boundary markers: The instructions do not explicitly mandate the use of delimiters or boundary markers (e.g., XML tags or "ignore instructions" wrappers) when the agent processes raw response text.
- Capability inventory: The skill environment includes tools for external communication and system mutation, such as
add-survey-recipients,send-survey-test-email,update-survey(for activation), andconfigure-survey-intercept. - Sanitization: There are no specific instructions regarding the validation or sanitization of response content before it is used for synthesis or follow-up tasks.
Audit Metadata