Difficult Conversations
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of educational Markdown documentation and interaction templates. It does not include any executable scripts, binaries, or system-level configuration files.
- [INDIRECT_PROMPT_INJECTION]: The skill includes sub-commands that process user-supplied descriptions of interpersonal conflicts to generate preparation guides.
- Ingestion points: User input provided to the
/difficultcommand and its variants in SKILL.md. - Boundary markers: The skill instructs the agent to use specific Markdown headers and structured blocks to organize its output.
- Capability inventory: The skill is restricted to standard platform tools (Read, Write, WebSearch) and does not implement any automated chains involving sensitive data access or unauthorized network transmission.
- Sanitization: Relies on standard LLM output generation and lacks custom sanitization scripts, which is typical for Markdown-only skills.
Audit Metadata