The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it processes external, potentially untrusted documents while having access to the Bash tool.\n- Ingestion points: Phase 1 (Analyze) requires reviewing external PRDs and system context in SKILL.md.\n- Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are defined for ingested requirements.\n- Capability inventory: The frontmatter grants access to powerful tools including Read, Grep, Glob, and Bash.\n- Sanitization: No sanitization or validation of the input content is specified in the design phase workflow.\n- [SAFE]: The skill's 'System Design Review Checklist' (reference/system-design-checklist.md) demonstrates strong security awareness by requiring reviews for SQL injection, XSS, and secrets management.\n- [SAFE]: No obfuscation, hardcoded credentials, or unauthorized remote code execution patterns were found in the skill's reference documents.

architect