confluence
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
@membranehq/clipackage via npm to facilitate interaction with Confluence through the Membrane platform. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it retrieves and processes untrusted data from external Confluence pages, blog posts, and comments.
- Ingestion points: Found in
SKILL.mdvia actions such aslist-pages,get-page,list-blog-posts,get-blog-post, andlist-page-comments. - Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore embedded instructions in the retrieved content.
- Capability inventory: The skill can execute network requests via the
membraneCLI and write data back to Confluence using actions likecreate-page,update-page, andcreate-page-comment. - Sanitization: There is no evidence of content sanitization or validation for the data ingested from Confluence.
Audit Metadata