marketing-media
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read marketing context from a local file, creating a surface where instructions embedded in that data could influence agent behavior.\n
- Ingestion points:
.agents/marketing-context.mdreferenced inSKILL.md.\n - Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings when processing the content of this file.\n
- Capability inventory: The skill uses tools for media generation and editing (
$image,$video).\n - Sanitization: Absent. There is no requirement in the instructions to validate or filter the content of the external context file.
Audit Metadata