bonus-stack-builder
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted product data and user-provided inputs, creating a vulnerability surface where malicious instructions embedded in product descriptions or external search results could influence agent behavior.
- Ingestion points: Product name, description, and URL fields defined in the input schema of
SKILL.md. - Boundary markers: Absent; the instructions do not utilize delimiters or specific warnings to ignore instructions that may be embedded within the external product data.
- Capability inventory: The skill is instructed to perform
web_searchoperations to research product gaps and complaints as specified in the workflow ofSKILL.md. - Sanitization: No explicit filtering, escaping, or validation of external input strings is defined before they are processed by the agent.
Audit Metadata