The Agent Skills Directory

[PROMPT_INJECTION]: No malicious instructions, safety bypasses, or jailbreak attempts were found in the skill body, metadata, or reference files.\n- [COMMAND_EXECUTION]: The skill executes a local Python helper script (scripts/next_adr_number.py) to determine the next ADR sequence number. Analysis of the script reveals it only performs local filesystem checks (listing files in specific directories) and contains no network code, subprocess calls, or sensitive file access.\n- [DATA_EXFILTRATION]: There are no network operations, hardcoded credentials, or commands that access sensitive user data such as SSH keys or environment secrets.\n- [REMOTE_CODE_EXECUTION]: The skill does not download, install, or execute any external packages or remote scripts.\n- [SAFE]: The skill is well-documented and its behavior strictly aligns with its stated purpose of generating architectural documentation.

adr-writing