social-post
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external text and media URLs, which is a standard attack surface for indirect prompt injection. \n
- Ingestion points: The
create_posttool inSKILL.mdtakes user input for the post content and media links. \n - Boundary markers: No explicit delimiters are suggested in the setup instructions for segregating user content. \n
- Capability inventory: The skill uses the Publora MCP server to perform legitimate network operations. \n
- Sanitization: The documentation does not specify content sanitization, which is typical for this type of API-based tool.
Audit Metadata