The Agent Skills Directory

[SAFE]: The skill provides legitimate security analysis instructions and templates. No malicious behaviors or patterns were found across the SKILL.md, examples, or template files.
[INDIRECT_PROMPT_INJECTION]: The skill operates on untrusted external data (system architecture and documentation), which is an inherent attack surface for indirect prompt injection.
Ingestion points: Uses Read, Grep, and Glob to process project-specific architectural information from the file system.
Boundary markers: The instructions do not define delimiters or specific 'ignore' directives to separate user-provided data from the core STRIDE analysis instructions.
Capability inventory: The skill allows the agent to create and modify documentation using Write and Edit tools.
Sanitization: Input data is processed directly without explicit sanitization or structural validation.

stride-analysis