marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill instructs the agent to read an external local file (
.claude/product-marketing-context.md) to gain product context. This is a known surface for indirect prompt injection where malicious instructions inside that file could influence the agent's behavior. - Ingestion points: File access to
.claude/product-marketing-context.mdspecified in the 'How to Use This Skill' section. - Boundary markers: Absent. The instructions do not define delimiters or warnings to ignore embedded instructions within the ingested file.
- Capability inventory: None. The skill contains only natural language instructions and lacks subprocess execution, file-writing, or network capabilities.
- Sanitization: Absent. There is no instruction to validate or escape the content retrieved from the context file.
Audit Metadata