Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent multi-agent software orchestration guide, but its broad triggers and full-scope agent-spawning/deployment workflow need review before use.
Install only if you intentionally want a full-scope multi-agent software-production workflow. Use it with explicit confirmation before spawning sessions, changing code, running CI/CD, or deploying, and consider narrowing its triggers if you want ordinary build or automation requests to stay local.
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
## Work Package: <ID>
### Objective
Clear statement of what this package delivers
### Inputs
- Specifications from: ...
The trigger list uses very broad terms such as 'automation', 'pipeline', 'orchestration', and 'build system', which can cause the skill to activate in ordinary software conversations where the user did not intend multi-agent orchestration. Because this skill includes agent spawning, code generation, and deployment-oriented workflows, overbroad activation increases the chance of unexpected automation or unsafe delegation.
Using 'build system' as a trigger can collide semantically with built-in or common 'build' commands, creating ambiguity about whether the user wants this skill or a standard build operation. In a skill that orchestrates agents and software production, such ambiguity can redirect routine build-related requests into broader autonomous workflows than intended.
The skill provides concrete agent-spawning commands and coordination patterns for implementation and review, but does not include an explicit warning that these actions may create code, launch sub-agents, or cause downstream system changes. In an orchestration skill, that omission is dangerous because users may invoke it without understanding that it can drive automated software production workflows with real operational effects.