The Agent Skills Directory

[SAFE]: The skill defines a legitimate development workflow for repository maintenance and releases. No malicious instructions, obfuscation, or unauthorized data access patterns were detected.
[COMMAND_EXECUTION]: The skill instructs the agent to perform standard development tasks using git, npm, pnpm, gh, and curl. These operations are strictly limited to the stated purpose of managing project releases and dependencies.
[EXTERNAL_DOWNLOADS]: The skill makes network requests to well-known and trusted services, specifically github.com and registry.npmjs.org, to verify package status and manage releases. These operations follow best practices for reliability, such as using HTTPS fallbacks and checking registry endpoints directly to bypass CDN caching.
[INDIRECT_PROMPT_INJECTION]: The skill processes project metadata and documentation (e.g., package.json, migration-guides/*.md). While this involves reading external content, the instructions are focused on structured versioning and deployment tasks, minimizing the potential for indirect instruction override. The risk is considered negligible within the context of the intended administrative use-case.

maintaining-lt-stack