content-posting
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [NO_CODE]: The skill references 11 JavaScript files (e.g.,
src/postThread.js,src/autoRepost.js,src/contentRepurposer.js) that are not included in the provided files. The underlying logic that performs automated actions on X/Twitter cannot be verified. - [INDIRECT_PROMPT_INJECTION]: The
contentRepurposer.jsandautoPlugReplies.jsfeatures ingest external data (existing tweets) to generate new content variations, creating a vulnerability surface. - Ingestion points: Existing tweets retrieved via
XActions.scan()and user-provided topics inXActions.create(). - Boundary markers: None identified in the provided configurations or descriptions.
- Capability inventory: Web navigation (
x.com), DOM manipulation for posting content, and state persistence. - Sanitization: No sanitization or validation logic is described for the processed tweet content.
- [COMMAND_EXECUTION]: The skill's documentation instructs users to copy and paste code directly into the browser console (
DevTools -> Console). This facilitates the execution of unverified logic within an authenticated session, which is a high-risk interaction model.
Audit Metadata