publish-x-article
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external Markdown files provided by the user and uses the extracted content to drive browser automation and clipboard operations. This creates a potential surface for indirect prompt injection attacks.
- Ingestion points: The agent reads and parses a local Markdown file (
article_md_path) provided as input. - Boundary markers: The instructions lack explicit boundary markers or warnings to the agent to treat the file content strictly as data and ignore any embedded natural language instructions.
- Capability inventory: The skill utilizes file system access (reading the source and writing to /tmp/), system clipboard access via Cocoa frameworks, and browser automation via Playwright to interact with x.com.
- Sanitization: While the
parse_markdown.pyscript converts Markdown to HTML using regex-based parsing, it does not include logic to filter or sanitize the content for potential injection strings.
Audit Metadata