launch-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions advise the agent to read marketing context from
.agents/product-marketing-context.mdto personalize the launch strategy recommendations. - Ingestion points: Context is read from the local
.agents/product-marketing-context.mdfile if present. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the context file.
- Capability inventory: The skill body consists of instructional guidelines and does not include subprocess execution or network requests.
- Sanitization: No explicit content sanitization or validation logic is specified for the ingested context file.
Audit Metadata