baoyu-danger-x-to-markdown
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands in
scripts/paths.tsto detect the Windows user profile directory when running under the Windows Subsystem for Linux (WSL), ensuring proper path resolution for local data storage. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from X (tweets and articles), which could potentially contain malicious instructions intended to mislead the agent when it reads the generated Markdown files.
- Ingestion points: Content is retrieved from external X GraphQL endpoints in
scripts/graphql.tsvia thefetchTweetResultandfetchXArticlefunctions. - Boundary markers: While the skill organizes output into Markdown blocks, it does not wrap the untrusted content in strong delimiters or provide explicit instructions to the agent to disregard instructions found within the external text.
- Capability inventory: The skill is capable of writing files to the local disk (for saving markdown and media assets) and making network requests to X domains.
- Sanitization: The skill implements basic escaping for Markdown characters in image alt-text within
scripts/markdown.ts, but it does not perform semantic filtering or sanitization of the fetched tweet or article bodies.
Audit Metadata