Security audit
Security checks for vulnerabilities and agentic risk
This skill is a DevRel strategy playbook made of markdown templates and does not request sensitive access, persistence, or automatic execution.
Install only if you want your agent to give structured DevRel and developer advocacy advice. Use explicit skill invocation to avoid accidental activation, and avoid sharing private business metrics, community data, or unpublished strategy unless you intend the agent to use that context.
The phrase Create DevRel strategy is an especially broad full-skill trigger that maps to a large portion of ordinary business language. Because it invokes the full multi-phase workflow, accidental activation could significantly misroute agent behavior, override a more appropriate tool, or consume unrelated user context at greater scope than narrower commands.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
The trigger phrase Audit our DX is broad and likely to overlap with ordinary user requests about developer experience. This can cause unintended invocation of the skill in contexts where the user did not explicitly request this specific DevRel workflow, leading to prompt-routing errors or inappropriate context capture.
The trigger phrase Plan conference strategy is ambiguous and can match common planning language unrelated to this skill. In agent ecosystems, ambiguous triggers increase the chance of accidental activation, causing the wrong capability to engage and potentially exposing unrelated conversation context to the skill.
The phrase Design SDK roadmap is generic and likely to occur in routine product or engineering discussions. Because it lacks boundaries or namespacing, it may unintentionally invoke the skill and steer the assistant into a structured workflow the user did not mean to trigger.
The trigger Open source strategy is underspecified and overlaps with a very common topic area. This creates a realistic risk of accidental skill activation during normal advisory conversations, which can degrade reliability and result in contextually inappropriate outputs.
No suspicious patterns detected.
