Security audit
Security checks for vulnerabilities and agentic risk
This skill is purpose-built for autonomous multi-agent delegation, but its broad automatic triggers and limited control gates make it something users should review carefully before installing.
Install only if you intentionally want macro-task delegation through autonomous sub-agents. Before use, review the planned agents, their input files, tool access, workspace paths, and outputs; avoid using it on sensitive repositories or private data unless you add explicit confirmation and scoping controls.
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
# Task: {TASK_NAME}
## Objective
{Clear statement of what needs to be accomplished}
## Context
{Background information relevant to the task}
Suspicious Unicode normalization or mixed-script content
The description also fails to warn that the skill delegates work to autonomous sub-agents that may act on generated instructions and process copied input files. In this skill's context, that omission is especially dangerous because the orchestrator dynamically generates sub-agent SKILL.md files and instructs agents to 'follow its instructions', creating a high-risk delegation chain where users may not appreciate the scope of autonomous actions being launched.
The description also fails to warn that the skill delegates work to autonomous sub-agents that may act on generated instructions and process copied input files. In this skill's context, that omission is especially dangerous because the orchestrator dynamically generates sub-agent SKILL.md files and instructs agents to 'follow its instructions', creating a high-risk delegation chain where users may not appreciate the scope of autonomous actions being launched.
The mandatory trigger list includes very broad phrases such as 'orchestrate', 'delegate tasks', and 'task breakdown' that are likely to match ordinary user requests and auto-activate this skill unexpectedly. Because this skill can spawn autonomous sub-agents and generate files, overbroad activation increases the chance of unrequested delegation, workspace creation, and task execution beyond user intent.