marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill introduces a potential indirect prompt injection surface by instructing the agent to ingest and process data from local context files to personalize its marketing advice.
- Ingestion points: The skill specifies several local file paths including
.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.mdinSKILL.md. - Boundary markers: No specific delimiters or safety instructions are defined to isolate the ingested context content from the agent's internal instructions.
- Capability inventory: The skill focuses on generating marketing recommendations, which requires the agent to utilize its file-reading tools to gather context.
- Sanitization: The instructions do not include any steps to validate or sanitize the content retrieved from the local context files before the agent processes it.
Audit Metadata