manage-team-lifecycle
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and metadata are focused on managing team lifecycle states within the RuFlo AI environment. The allowed tools are restricted to vendor-specific management functions. No malicious patterns such as credential theft, obfuscation, or unauthorized command execution were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data which presents a theoretical surface for indirect prompt injection.
- Ingestion points: External team data is accessed via the mcp__plugin_ruflo-ai-team_ruflo-ai-team__team_get tool (SKILL.md).
- Boundary markers: The instructions do not specify delimiters or warnings to ignore instructions embedded within the ingested data.
- Capability inventory: The skill can perform team updates through mcp__plugin_ruflo-ai-team_ruflo-ai-team__team_update and evidence exports via mcp__plugin_ruflo-ai-team_ruflo-ai-team__evidence_export (SKILL.md).
- Sanitization: No specific sanitization or validation of content returned by the tools is defined.
Audit Metadata