Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad activation metadata, but no evidence of hidden code, persistence, credential access, exfiltration, or destructive behavior.
Install only if you want a general proactive-agent workflow helper. Be aware it may be selected for ordinary productivity or bug-fix requests because its triggers are broad and implicit invocation is enabled; prefer explicit invocation if your platform supports it.
The trigger phrases are generic enough to match ordinary user requests such as asking for help, needing a workflow, or handling a task. In an agent ecosystem, this can cause the skill to activate unintentionally, hijacking unrelated conversations and inserting workflow behavior where the user did not explicitly request this skill.
The trigger phrases are broad, generic, and overlap with normal user language such as asking for help or requesting a practical workflow. This can cause unintended activation of the skill in unrelated contexts, which is a security and reliability concern because the skill may influence responses when the user did not explicitly intend to invoke it.
The manifest description says to use the skill when a user asks for broad categories like 'work-productivity', 'proactive', 'transform', 'task', or any practical workflow or checklist, which is ambiguous enough to match a very large portion of normal user requests. This can lead to over-invocation and misapplication of the skill, making agent behavior less predictable and potentially interfering with safer or more specialized skills.
The trigger keywords are extremely broad, including generic terms like 'task', 'transform', 'needs', and 'partners', which can cause the skill to activate in many unrelated conversations. Overbroad activation increases the chance of unintended routing, shadowing more appropriate skills, and causing the agent to apply this workflow in contexts where its assumptions or outputs are not safe or relevant.
The manifest description says the skill should be used for broad categories like work-productivity, proactive-agent, proactive, transform, and task, which are ambiguous and likely to overlap with many unrelated user requests. This increases accidental invocation risk, making the system less predictable and potentially causing the wrong skill to handle user input.
The trigger list is overly broad and includes common words such as “task,” “needs,” and “bug fix,” which can cause the skill to activate during ordinary conversations unrelated to this skill’s intended purpose. In an agent ecosystem, this creates routing confusion and can unexpectedly inject this skill’s workflow into unrelated tasks, reducing reliability and potentially causing inappropriate automation or advice to be applied.
The manifest sets allow_implicit_invocation: true without any visible trigger constraints, scoping rules, or narrow routing conditions. This can cause the skill to be auto-selected for broad, ordinary user requests, increasing the chance of prompt-scope overreach, unintended activation, and misuse in contexts the user did not explicitly request.
The trigger examples include broad natural-language phrasing such as 'Help me' and 'I need a practical workflow' tied to a wide problem space, which can cause the skill to activate for many ordinary requests that were not meant to invoke it. In an agent ecosystem, overbroad activation can lead to unintended routing, inappropriate disclosure of context to the skill, and execution of the wrong workflow when users discuss adjacent tasks.
This Chinese README contains substantial English instructional content and trigger text, but does not state whether the skill should operate in Chinese, English, or based on user preference. That can amount to an implicit language policy without user opt-in.
The example trigger sentences are truncated, repetitive, and do not show realistic boundaries for when the skill should or should not be used. Poor examples reinforce the already overbroad activation logic and make it more likely that integrators or automated routing systems will treat generic productivity requests as matching this skill.
The default prompt uses broad, generic phrasing like 'help me' and references a wide class of workflow assistance, which can overlap with many normal user requests. Combined with implicit invocation, this increases the likelihood that the skill is invoked when the user did not intend to use it, potentially injecting irrelevant or unsafe behavior into unrelated conversations.
The invocation guidance does not clearly define mandatory conditions, exclusions, or disambiguation logic, so other generic work-productivity requests may accidentally match this skill. In a proactive-agent context, ambiguous routing is more dangerous because the skill is designed to continue with assumptions and produce artifacts, increasing the chance of unintended actions or misleading outputs from a mistaken activation.
