x-api-v2
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates interaction with untrusted external content, creating a potential attack surface for indirect prompt injection. \n- Ingestion points: Multiple GET operations such as 'searchPostsRecent', 'getUsersMentions', and 'getDirectMessagesEvents' (references/operations/) ingest content created by external users. \n- Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore commands within retrieved content. \n- Capability inventory: The skill provides significant write access via operations like 'createPosts', 'deleteLists', and 'repostPost' (references/operations/). \n- Sanitization: No procedures for sanitizing or filtering external content before processing are defined in the documentation.
Audit Metadata