The Agent Skills Directory

[Prompt Injection] (SAFE): No instructions to override safety filters or agent behavior were detected. The skill contains standard operational instructions and escalation triggers for project management.\n- [Data Exposure & Exfiltration] (SAFE): The skill does not perform network operations or access sensitive filesystem locations. No hardcoded credentials or secrets are present.\n- [Obfuscation] (SAFE): All content is human-readable markdown. No Base64, zero-width characters, or homoglyphs were found.\n- [Unverifiable Dependencies & RCE] (SAFE): No external dependencies, package files, or remote code execution patterns were identified across the 17 files.\n- [Indirect Prompt Injection] (SAFE): The skill defines a framework for processing artifacts but lacks the capabilities (e.g., code execution or network writes) that would make it vulnerable to indirect injection. [Ingestion points]: Agent-processed project artifacts. [Boundary markers]: YAML frontmatter and Markdown sections. [Capability inventory]: None. [Sanitization]: None.

project-planning