marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: LOWPROMPT_INJECTION
Full Analysis
- [Prompt Injection] (LOW): Surface for indirect prompt injection identified through automatic file ingestion. • Ingestion points: The skill instructions explicitly direct the agent to check and read '.claude/product-marketing-context.md' if it exists. • Boundary markers: Absent. The skill does not provide delimiters or instructions to the agent to treat the content of the file as untrusted or to ignore embedded instructions. • Capability inventory: Ingested content is used to influence the agent's reasoning, strategic recommendations, and generated marketing ideas. • Sanitization: Absent. No validation, filtering, or escaping is applied to the data retrieved from the context file.
Audit Metadata