The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of PRDs and feature specifications, which represents a potential surface for indirect instructions.
Ingestion points: Processes external files through the /design:workflow command and requirements analysis steps defined in both SKILL.md and references/workflow.md.
Boundary markers: The instructions do not specify the use of delimiters or boundary markers to isolate the untrusted external content from the agent's core instructions.
Capability inventory: The skill utilizes the Read, Write, TodoWrite, and WebSearch tools, and can delegate tasks to Explore, general-purpose, and code-reviewer subagents.
Sanitization: No explicit sanitization, validation, or filtering of the input data is described in the skill instructions.
[SAFE]: No malicious patterns such as obfuscation, credential exfiltration, persistence mechanisms, or unauthorized privilege escalation were detected. The skill's behaviors, including the use of specialized MCP servers for context and memory management, are consistent with its stated purpose of project planning and task decomposition.

implementation-workflow