nuget-manager
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes repository configuration files and dependency lock files which may contain embedded instructions from external sources. * Ingestion points: Workflow step 1 in SKILL.md involves inspecting existing files and dependency trees. * Boundary markers: Instructions in SKILL.md require the agent to restate constraints and get user confirmation for all implementations. * Capability inventory: The agent can execute shell commands via the dotnet CLI and call vendor APIs as defined in SKILL.md and references/sandbase-api-map.md. * Sanitization: External data is not explicitly sanitized or filtered before processing.
- [COMMAND_EXECUTION]: The skill utilizes the dotnet CLI to perform standard package management tasks such as restore, build, and test.
- [EXTERNAL_DOWNLOADS]: The skill retrieves dependencies from official registries and interacts with vendor-provided APIs for external documentation and inference.
Audit Metadata