The Agent Skills Directory

[SAFE]: The skill is restricted to read-only operations. It contains explicit instructions to never modify files and provides a structured workflow for navigating documentation without altering content.
[COMMAND_EXECUTION]: The skill uses the rg (ripgrep) utility to perform searches within the breadcrumbs-docs-vault/ directory. This is a standard and expected use of search tooling for a navigation skill.
[DATA_EXFILTRATION]: There are no network-enabled commands (e.g., curl, wget) or instructions to access sensitive system files like credentials, SSH keys, or environment variables.
[PROMPT_INJECTION]: The instructions provide clear operational guidelines for the agent without attempting to override system prompts, bypass safety filters, or use role-play for malicious purposes.
[SAFE]: Analysis of the skill body and metadata reveals no obfuscation (such as Base64 or hidden characters), remote code downloads, or privilege escalation attempts.

breadcrumbs-nav