linkedin-to-x
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and follow instructions from external sources, which can be manipulated to override agent behavior.
- Ingestion points: The skill reads settings from
.liftli/voice.mdand~/.liftli/voice.md, and follows instructions returned by thestrategist_briefingtool. - Boundary markers: Absent. The instructions "read it and follow it" and "follow Liftli's instructions" do not provide delimiters or warnings to ignore potentially malicious embedded commands.
- Capability inventory: The skill primarily performs text transformation and provides installation instructions to the user.
- Sanitization: Absent. There is no mention of validating or filtering the content retrieved from these external files or tools.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for the user to download and install additional components.
- Evidence: Recommends running
npx skills add liftli-ai/linkedin-agent-skillsand adding an MCP server viahttps://mcp.liftli.ai/mcp. - Context: These resources originate from the skill's author (
liftli-ai) and represent the intended extension of the vendor's ecosystem.
Audit Metadata