The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the project's codebase without sufficient sanitization or boundary markers.\n
Ingestion points: Reads go.mod, .modernize, and project source files using Read, Glob, and Grep tools.\n
Boundary markers: Absent; there are no instructions to the agent to treat file content as data only or to ignore embedded instructions.\n
Capability inventory: The skill has extensive capabilities including file modification (Edit, Write), command execution (Bash for go, git, and golangci-lint), and sub-agent invocation.\n
Sanitization: Absent; the skill does not define filters or validation steps for the content of the files it analyzes.\n- [SAFE]: The skill incorporates strong security recommendations, such as using os.Root to prevent path traversal and govulncheck to identify reachable vulnerabilities in dependencies.\n- [SAFE]: The skill limits its command execution environment to specific, well-known development tools (go, git, golangci-lint), reducing the risk of arbitrary system command execution.\n- [SAFE]: External resources and downloads refer to official Go project domains or the author's recognized repositories, with no evidence of typosquatting or malicious redirection.

golang-modernize