post-editing
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the user or agent to execute JavaScript code via the browser's developer console on x.com, which allows interaction with the web application's internal session and DOM.
- [EXTERNAL_DOWNLOADS]: The skill relies on an external script file 'src/editPost.js' containing the core logic, which is not included in the primary instruction file.
- [DYNAMIC_EXECUTION]: The instructions involve pasting and running JavaScript in a live browser session, representing dynamic execution in a sensitive authenticated environment.
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through untrusted user data. (1) Ingestion point: 'newText' variable in the CONFIG object in SKILL.md. (2) Boundary markers: None present to distinguish instructions from content. (3) Capability inventory: DOM manipulation and automated submission of posts on X.com. (4) Sanitization: No sanitization or validation of the input text is mentioned.
Audit Metadata