difficult-situations
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructional text and frameworks for management advice. It does not contain executable code or malicious patterns.
- [EXTERNAL_DOWNLOADS]: Includes an informational reference to a blog post on kellanem.com for additional context on layoffs. This link is for user reading and does not involve automated downloads or execution.
- [DATA_EXFILTRATION]: The skill accesses local organizational context files (e.g., .agents/em-context.md) to personalize advice, but it does not possess tools or instructions for network communication, preventing data exfiltration.
- [SAFE]: Regarding potential Indirect Prompt Injection (Category 8), the skill ingests data from employee reports in .agents/reports/ (Ingestion point). While boundary markers and sanitization are absent, the skill has an empty capability inventory (no command execution or network access), mitigating exploitation risks.
Audit Metadata