twitter-thread-creation
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references an installation guide for the
infshCLI located on the author's official GitHub repository (inference-sh/skills). - [COMMAND_EXECUTION]: The skill uses the
infshtool to execute various application runs, such as posting to X, converting HTML to images, and browsing web pages for research. - [PROMPT_INJECTION]: The skill facilitates the ingestion of external data via web search (
tavily/search-assistant) and browser actions (infsh/agent-browser) to generate content. This creates a surface for indirect prompt injection where malicious content on a searched website could influence the agent's output. - Ingestion points: Tavily search results and browser screenshots/content (referenced in SKILL.md).
- Boundary markers: None identified in the provided templates.
- Capability inventory: Subprocess calls via
infshfor social media posting and browser interaction. - Sanitization: No explicit sanitization or validation of the retrieved web content is shown in the examples.
Audit Metadata