launch-announcement
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external content and user input while maintaining high-impact capabilities.
- Ingestion points: Data enters the context through user-provided launch facts in SKILL.md (Step 1), media retrieved from URLs in
upload_media_from_url(Step 5), and existing post data fromlist_posts_advanced(Step 2). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to isolate untrusted data from the core logic.
- Capability inventory: The skill has access to tools that can modify the user's social media accounts, such as
bulk_create_posts,update_post, anddelete_post. - Sanitization: No explicit sanitization or content validation steps are described in the instructions to protect against instructions embedded in external sources.
Audit Metadata