schedule-week
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data to generate social media content, which presents a surface for indirect prompt injection.
- Ingestion points: External data is ingested via user input in Step 1.4, including topics, content pillars, and source material.
- Boundary markers: The skill provides strong human-in-the-loop mitigations by requiring explicit user approval of the plan in Step 2 and a final review of all full post content in Step 4 before any scheduling tool is executed.
- Capability inventory: The skill has the capability to write and schedule content to external platforms using tools such as
publish,update_post, anddelete_post. - Sanitization: No specific input sanitization or filtering logic is mentioned for the processed user content, though the manual review process serves as the primary safeguard.
Audit Metadata