marketing-ideas
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to read and follow context from
.agents/product-marketing-context.mdor.claude/product-marketing-context.mdif they exist. - Ingestion points: The file
.agents/product-marketing-context.mdis specified as a context source inSKILL.md. - Boundary markers: The instructions lack explicit boundary markers or directives to ignore instructions that may be embedded within the context file.
- Capability inventory: The skill provides textual marketing recommendations and does not explicitly call dangerous system tools, though it functions within a general-purpose agent context.
- Sanitization: No validation, sanitization, or filtering mechanisms are defined for the data read from these context files.
Audit Metadata