stakeholders-org-design
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional text, methodologies, and structured templates for organizational planning. It does not attempt to execute shell commands, access sensitive file system paths, or perform unauthorized network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied data regarding stakeholders and organizational initiatives, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill accepts untrusted user input describing organization members, stakeholder roles, and initiative descriptions within the mapping workflow in
SKILL.mdandresources/template.md. - Boundary markers: There are no explicit boundary markers or instructions for the agent to ignore potentially malicious embedded content within the user-provided data.
- Capability inventory: The skill's capabilities are limited to text analysis and framework generation; it does not request dangerous tools or perform dynamic code execution.
- Sanitization: No explicit input sanitization or validation mechanisms are defined for the data processed by the skill.
Audit Metadata