use-good-answers-as-templates
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions facilitate the ingestion of untrusted external data into the agent's prompt context.
- Ingestion points: The prompt templates in SKILL.md contain placeholders for external content including '[PASTE YOUR FAVORITE PAST RESPONSE HERE]' and '[PASTE RAW NOTES / DATA FOR THE NEW ITEM]'.
- Boundary markers: The skill suggests using '<exemplar_format>' tags as delimiters to separate reference examples from instructions.
- Capability inventory: There are no executable scripts or tool-calling definitions associated with this skill.
- Sanitization: No validation or sanitization protocols are suggested for the external data being ingested.
Audit Metadata