01-content-calendar-global
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from an external local file.
- Ingestion points: The skill reads brand and regional configuration from
.agents/product-marketing-context-global.mdin 'Step 0'. - Boundary markers: The instructions do not define clear delimiters or specific instructions to disregard potential commands embedded within the context file.
- Capability inventory: The skill lacks dangerous capabilities such as network exfiltration, arbitrary command execution, or file system writing, which mitigates the risk of an injection being exploited.
- Sanitization: There is no evidence of sanitization or validation performed on the ingested data before it is incorporated into the agent's context.
Audit Metadata