linkedin-engagement-rate
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied post statistics (impressions, followers, and engagement metrics) to perform calculations.
- Ingestion points: User-provided numbers and stats shared in the chat context are processed by the formulas in
SKILL.md. - Boundary markers: None present; the skill treats numeric inputs as data for calculation.
- Capability inventory: No high-risk capabilities detected. The skill performs arithmetic and outputs text-based benchmarks without file system access, network writes, or shell execution.
- Sanitization: None; input is interpreted mathematically.
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for the user to manually add an external MCP server using the command
claude mcp add --scope user --transport http liftli https://mcp.liftli.ai/mcp. This points to a vendor-owned resource for extending functionality within supported environments like Claude Code.
Audit Metadata