linkedin-limits-and-safety
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed entirely of informational Markdown files (
SKILL.md,references/caps-and-rules.md,references/health-report.md,references/warning-signs.md). It contains no scripts, binary executables, or instructions that trigger automated network or system operations. - [INDIRECT_PROMPT_INJECTION]: The skill defines a framework for the agent to process user-provided LinkedIn metrics (e.g., acceptance rates, invite counts) to generate a health report.
- Ingestion points: Data enters the context when a user provides weekly metrics for the 'Monday health check' described in
references/health-report.md. - Boundary markers: The skill provides a structured template and explicit 'Verdict rules' to guide the agent's output, reducing the risk of the agent deviating from the intended reporting format.
- Capability inventory: The skill has no capabilities for code execution, file system modification, or network requests.
- Sanitization: None present, but the lack of high-privilege tools makes the surface non-exploitable.
Audit Metadata