product-appeal-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze external content fetched via the
WebFetchtool, creating a vulnerability to indirect prompt injection where malicious instructions hidden in websites could influence the agent's behavior. - Ingestion points: Target URLs retrieved using the
WebFetchtool during the analysis workflow defined inSKILL.md. - Boundary markers: There are no specified delimiters or instructions for the agent to disregard potential commands embedded within the external content.
- Capability inventory: The skill is configured with
Read,Write,Edit, andWebFetchpermissions in theSKILL.mdfrontmatter. - Sanitization: The instructions do not define any sanitization, filtering, or validation steps for content retrieved from external sources.
Audit Metadata