The Agent Skills Directory

[SAFE]: The skill is entirely declarative and focuses on reading specific markdown and JSON files from the local context to format a report.\n- [DATA_EXPOSURE_AND_EXFILTRATION]: Access is limited to internal project documentation (e.g., active-bets.md, registry.md). There are no network requests (curl, wget, or fetch) or attempts to access sensitive system paths like SSH keys or environment secrets.\n- [REMOTE_CODE_EXECUTION]: No external dependencies, package installations (npm/pip), or remote script executions are present.\n- [PROMPT_INJECTION]: Instructions are focused on data processing and report formatting. No attempts to override safety guidelines or bypass agent constraints were detected.\n- [OBFUSCATION]: No encoded content, hidden characters, or deceptive naming patterns were found in the instructions or metadata.

portfolio-status