The Agent Skills Directory

[SAFE]: The provided Python script (scripts/codebase_analyzer.py) utilizes only Python's standard libraries to perform local file system analysis. It does not perform network operations, execute external code, or read the actual content of files beyond checking for their existence and metadata (e.g., size).
[SAFE]: Documentation templates (references/onboarding-template.md and references/output-format-templates.md) follow security best practices by using environment variable placeholders (e.g., $CONFLUENCE_TOKEN, NOTION_TOKEN) and .env.example files instead of hardcoding sensitive credentials.
[SAFE]: No patterns of prompt injection, obfuscation, or persistence mechanisms were detected in the instructions or the accompanying scripts.
[SAFE]: The skill ingestion surface (analyzing untrusted codebases) is handled via metadata extraction (file names and sizes), which presents a negligible risk for indirect prompt injection given the script's limited capabilities.

codebase-onboarding