The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and reasoning guidelines. No executable scripts, binaries, or automated setup tasks are included.
[INDIRECT_PROMPT_INJECTION]: The skill instructions guide the agent to analyze external project data such as source code, commit history, and issue logs (ingestion points identified in references/informal-verification.md). While this establishes a surface for indirect prompt injection where malicious content in analyzed files could attempt to steer agent behavior, the risk is inherent to the general task of repository analysis and is not exacerbated by any dangerous tools or scripts within the skill itself. Boundary markers and sanitization steps are not explicitly defined in the skill instructions.
[EXTERNAL_DOWNLOADS]: The reference materials contain links to well-known documentation sites and an established GitHub repository for software laws. These resources are informational and do not involve the runtime download or execution of unverified code.

software-laws