launch-announcement
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill features a surface for indirect prompt injection as it interpolates user-provided product details and links into social media post templates.\n
- Ingestion points: User-supplied facts requested in Step 1 of
SKILL.md(launch details, links, prices, offer terms).\n - Boundary markers: Absent. The instructions do not mandate the use of delimiters or specific markers to isolate user-provided data from the post-generation instructions.\n
- Capability inventory: The skill possesses the capability to publish content via
bulk_create_postsand retrieve external media assets viaupload_media_from_url.\n - Sanitization: Absent. The skill does not explicitly perform validation or sanitization on the inputs before they are included in social media posts.
Audit Metadata