free-tools
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions include a check for context files such as
.agents/product-marketing.mdor.claude/product-marketing.md. While these serve as ingestion points for external data, the skill lacks any dangerous capabilities (e.g., file system modifications, network requests, or shell execution) that could be exploited via injection. - Ingestion points: Reads from
.agents/product-marketing.mdor.claude/product-marketing.mdas specified inSKILL.md. - Boundary markers: No specific delimiters defined for the ingested context.
- Capability inventory: None. The skill only provides conversational strategy advice and has no defined tools or script actions.
- Sanitization: Not applicable as the skill performs no automated actions beyond providing text-based recommendations.
Audit Metadata