marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read product-specific context from local workspace files such as
.agents/product-marketing.mdbefore proceeding with recommendations. - Ingestion points: Accesses and processes content from
.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.md(SKILL.md). - Boundary markers: The skill lacks explicit delimiters or instructions for the agent to ignore potentially malicious commands embedded within these external context files.
- Capability inventory: The skill is designed for strategic advice and does not include tools for network operations, file writing, or shell command execution.
- Sanitization: There is no evidence of sanitization or content validation for the data ingested from the context files.
Audit Metadata