go-preship-check
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to have the agent analyze external Go codebases provided by the user. This creates a vulnerability where malicious instructions embedded in the code (such as in comments or string literals) could attempt to influence the agent's behavior.
- Ingestion points: The skill ingests user-specified files and packages for review (SKILL.md).
- Boundary markers: The instructions lack specific delimiters or warnings to the agent to disregard instructions found within the code being analyzed.
- Capability inventory: The skill utilizes shell execution capabilities to run the Go toolchain (
go vet,go test) and linters. - Sanitization: No sanitization or filtering of the input code is performed before analysis.
- [COMMAND_EXECUTION]: The skill explicitly directs the agent to execute shell commands including
go vet ./...,go build -gcflags="-m",staticcheck ./...,go test -race ./..., andgolangci-lint run. While these are standard, legitimate development tools, they represent a significant capability tier that could be abused if the agent is misled by the content of the code it is auditing.
Audit Metadata