positioning-and-offer
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is configured to ingest external context from a specific file (
.agents/marketing-context.md) if it is present in the environment. While this allows external data to influence the agent's output, the skill's capabilities are limited to generating text deliverables, minimizing the risk of exploitation. - Ingestion points:
.agents/marketing-context.md(referenced inSKILL.md). - Boundary markers: None identified in the prompt instructions.
- Capability inventory: The skill produces text-based strategic deliverables (positioning statements, offer specifications, message hierarchies). No file-system write operations, network requests, or subprocess executions are defined in the provided files.
- Sanitization: No explicit sanitization or validation of the context file content is performed.
Audit Metadata