The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill utilizes Bash and Edit tools to validate implementation phases and update project files. These tools are used as intended for coordination and do not include patterns for unauthorized command execution or privilege escalation.
[PROMPT_INJECTION] (SAFE): No direct instructions to bypass safety guardrails or extract system prompts were detected in the skill content.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill reads from potentially untrusted data sources to drive its logic, creating a surface for indirect injection. 1. Ingestion points: PLAN.md and outputs from sub-agents via the Task tool. 2. Boundary markers: Absent; the skill lacks explicit delimiters or instructions to ignore embedded commands within the ingested content. 3. Capability inventory: The skill has access to Bash, Edit, and Task tools, which provide a significant surface for file modification and command execution. 4. Sanitization: No sanitization or validation of the input data is described before it is processed by the agent.

agent-coordination