Security audit
Security checks for vulnerabilities and agentic risk
The skill is a documentation-only workflow helper with overly broad activation wording but no hidden code, persistence, credential handling, or destructive behavior.
Install only if you want a broad workflow helper for ontology-style productivity and skill-authoring tasks. Because implicit invocation is enabled with generic keywords, users or maintainers may want narrower triggers to reduce accidental activation, but no malicious or high-risk behavior was found.
The skill description and activation guidance are broad enough to match many ordinary requests about productivity, workflows, knowledge, or implementation help. This can cause unintended invocation of the skill, leading to scope confusion, prompt-routing errors, and increased exposure to any unsafe behavior or bad assumptions embedded in the skill.
The keyword list includes highly generic terms such as 'knowledge', 'graph', 'structured', 'creating', and 'bug fix', which are common across unrelated conversations. In a skill-routing system, this creates a high risk of overmatching, causing the skill to activate in contexts where it is not appropriate and potentially override safer or more relevant behavior.
Enabling implicit invocation without tightly scoped activation criteria allows the platform to invoke this skill based on vague semantic similarity rather than clear user intent. In combination with the broad productivity-oriented description and prompt, this can cause unintended invocation across many normal conversations, increasing the attack surface for prompt injection, data overexposure, and confused-deputy behavior.
The trigger sentence is broad enough to match ordinary user phrasing about help, workflows, or bug fixing, which can cause the skill to activate outside its intended scope. In an agent ecosystem, overly broad activation can route unrelated requests into this skill, creating prompt-surface expansion, mis-execution, and increased chance of unsafe or irrelevant actions being taken under the wrong workflow.
The trigger sentences are generic enough that ordinary user requests about work productivity, ontology, or practical workflows could invoke the skill unintentionally. In an agent ecosystem, overbroad activation can cause the wrong skill to run, leading to irrelevant actions, confused tool selection, or unsafe downstream behavior if the skill is applied outside its intended scope.
The trigger phrases are generic and likely to match ordinary user requests unrelated to this specific skill, which can cause the agent to invoke the skill unexpectedly. In an agent ecosystem, over-broad activation can hijack routing, produce irrelevant outputs, and increase the chance that this skill handles requests outside its intended safety and capability boundaries.
The example triggers use ordinary phrases like 'Help me' and 'I need a practical workflow', which are common in normal user requests and therefore encourage ambiguous activation patterns. Even if the author intended only illustrative examples, these phrases may train or bias routing logic toward activating the skill too broadly.
The skill description defines a very wide problem space covering workflow help, bug fixing, hardening, reliability, adjacent skill creation, checklists, analysis, and implementation support. Because the boundaries are unclear, the agent may select this skill for many loosely related requests, increasing the chance of misapplication, unsafe assumptions, or bypass of more specialized controls.
The trigger keywords are very broad and include common terms like "knowledge", "graph", "structured", and "creating", which can match many unrelated requests. This can cause the skill to activate outside its intended domain, leading to incorrect routing, over-broad assistance, or accidental influence over tasks that should be handled by a more appropriate skill.
The default prompt is extremely broad and phrased in natural language that overlaps with common user requests about productivity, workflows, checklists, analysis, and implementation help. This increases the chance the skill will be auto-selected in situations the user did not intend, causing prompt-scope creep, unexpected tool routing, or unsafe delegation to a skill handling adversarial content.
The activation examples do not clearly separate valid invocation cases from common requests, so the skill may be selected for ambiguous tasks it was not designed to handle. This is dangerous because misrouting in agent systems can bypass safer or more appropriate skills, leading to incorrect outputs, unintended autonomy, or abuse through prompt phrasing crafted to force activation.
