golang-troubleshooting
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill configuration specifies the installation of the Delve debugger from a well-known community repository using the standard Go package manager. This is a routine operation for Go development environments.
- Evidence:
github.com/go-delve/delve/cmd/dlv@latestinstalled viago install. - [COMMAND_EXECUTION]: The skill is configured to allow the execution of specific, standard developer CLI tools. The execution scope is limited to tools required for debugging and codebase management.
- Evidence: Allowed tools include
Bash(go:*),Bash(golangci-lint:*),Bash(git:*), andBash(dlv:*). - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and process external content including source code and tool outputs.
- Ingestion points: The skill reads project source files (
**/*.go), captures output from CLI tools (build errors, test failures, stack traces), and potentially fetches external web content. - Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the processed data.
- Capability inventory: The agent has permissions to write to the filesystem and execute shell commands within a restricted toolset.
- Sanitization: No explicit sanitization or filtering of external content before processing is documented in the skill instructions.
Audit Metadata