pricing-strategy
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest content from external files like
.agents/product-marketing-context.mdat the start of a session. This could allow instructions hidden in those files to influence the agent's behavior. - Ingestion Point: Referenced in
SKILL.mdbefore the business context section. - Boundary Markers: No delimiters or specific instructions are provided to distinguish between data and potential instructions within the context files.
- Capability Inventory: The skill is entirely instructional and does not include any scripts, network access, or dangerous command execution tools.
- Sanitization: The skill does not define any methods for sanitizing or validating the content of the external context files.
Audit Metadata