conflict-deescalation
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown text providing guidance on conflict resolution. It does not contain any scripts, binary files, or configuration that would allow for code execution or network communication.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided text (descriptions of conflicts and recent exchanges). While this constitutes an attack surface for indirect prompt injection, the skill lacks any actionable capabilities—such as file system access, network requests, or subprocess execution—that could be leveraged for malicious purposes. The risk is negligible as it only outputs interpersonal advice.
- Ingestion points: Required inputs in SKILL.md ('The conflict', 'What was said').
- Boundary markers: None explicitly defined.
- Capability inventory: No scripts or tools are utilized; the skill has no system-level capabilities.
- Sanitization: Not applicable as there is no downstream execution.
Audit Metadata