devexpress-winforms-tab-control
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to fetch documentation from an external MCP service, which creates an ingestion point for untrusted data into the agent's execution context.\n
- Ingestion points: The agent is instructed to use
devexpress_docs_searchanddevexpress_docs_get_contenttools to retrieve information from external documentation servers (SKILL.md).\n - Boundary markers: The skill includes explicit instructions to treat documentation as reference content only and to ignore any behavioral directives or commands found in the fetched content (SKILL.md).\n
- Capability inventory: The skill allows the agent to execute shell commands for building projects (
dotnet build) and perform file system modifications (SKILL.md).\n - Sanitization: The skill relies on instructional guardrails to mitigate risks from external content rather than technical sanitization or validation.
Audit Metadata