The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified. The skill's functionality is strictly limited to local codebase analysis and documentation updates through natural language interaction.\n- [NO_CODE]: The skill consists exclusively of Markdown instructions and templates (CONTEXT-FORMAT.md, ADR-FORMAT.md). It does not contain any scripts, executables, or binary files.\n- [COMMAND_EXECUTION]: While the skill instructions involve codebase exploration and file updates, these are restricted to standard documentation management tasks. No dangerous shell commands, privilege escalation attempts, or persistent mechanisms were found.\n- [DATA_EXFILTRATION]: No network operations or patterns associated with sending sensitive data to external servers were identified. The skill does not utilize network-enabled tools like 'curl' or 'wget'.\n- [PROMPT_INJECTION]: The skill's instructions establish a specific persona but do not contain attempts to override the agent's safety protocols, extract system prompts, or bypass ethical guidelines.

interrogate-me