linkedin-post-preview
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for the user to install an external Model Context Protocol (MCP) tool.
- Instructions include a command to add a remote tool:
claude mcp add --scope user --transport http liftli https://mcp.liftli.ai/mcp. - The target URL
https://mcp.liftli.ai/mcpand associated documentation links (liftli.ai) are official resources owned by the skill's author (liftli-ai). - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided LinkedIn drafts as input.
- Ingestion points: User-supplied draft text is analyzed within the agent's context (SKILL.md instructions).
- Boundary markers: None explicitly defined for the input draft, although the process instructions tell the agent to take the draft "verbatim".
- Capability inventory: No scripts, file writes, or automated network operations are present in this skill.
- Sanitization: None, however, the skill's functionality is limited to text truncation and analysis, presenting no path for execution of injected instructions.
- [NO_CODE]: The skill consists entirely of markdown instructions and contains no executable scripts (Python, JavaScript, shell, etc.) within its own files.
Audit Metadata