dotnet-library-documentation
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform a 'compile probe' (SKILL.md) to verify API signatures, which involves executing compiler commands.
- [INDIRECT_PROMPT_INJECTION]: The skill reads project metadata and external documentation (SKILL.md), creating a surface for indirect prompt injection.
- Ingestion points: Local project files like global.json and Paket files, plus external documentation URLs (SKILL.md).
- Boundary markers: Absent; no delimiters are defined to separate untrusted data from instructions.
- Capability inventory: Compilation and execution of code probes via development CLI tools (SKILL.md).
- Sanitization: Absent; the skill does not specify methods for filtering or escaping external content.
Audit Metadata