recycle-top-posts
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface for indirect prompt injection as it processes untrusted historical content from external social media platforms.
- Ingestion points: Historical post data is retrieved from external platforms using the
list_posts_advancedandget_posttools. - Boundary markers: There are no explicit instructions to use delimiters or ignore instructions that may be embedded within the retrieved post content.
- Capability inventory: The skill has the ability to write to the platform by creating drafts or scheduling posts via
bulk_create_posts. - Sanitization: No explicit sanitization or filtering of the retrieved content is performed before it is rewritten by the agent.
Audit Metadata