apps-manage-registration-pages
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified. The skill follows best practices by requiring user confirmation for write operations and using dry-run modes for previews. It also prevents secret leakage by instructing the agent not to ask for environment variables in chat.
- [INDIRECT_PROMPT_INJECTION]: The skill processes contractor records from an external API, which represents a potential injection surface. However, it mitigates risks by instructing the agent to filter personal fields and provide summarized results.
- Ingestion points: Contractor data is retrieved via the
apps_list_advance_plan_contractorstool (SKILL.md). - Capability inventory: The skill can modify registration plans using
apps_create_advance_plan,apps_update_advance_plan, andapps_delete_advance_plan(SKILL.md). - Boundary markers: The skill does not define specific prompt delimiters for external data, but instructs the agent to return only specific fields (SKILL.md).
- Sanitization: Instructions mandate omitting unrelated personal fields and prohibit saving or reproducing the raw list (SKILL.md).
Audit Metadata