Security audit
Security checks for vulnerabilities and agentic risk
This is a broad developer-workflow helper with no executable payload; the main risk is overbroad automatic activation.
This skill is acceptable to install, but expect it to activate broadly for developer and GitHub-related requests. Review its output before applying code changes or workflow changes, especially when repository state or public GitHub content could be affected.
The trigger phrases are broad enough to match many ordinary software-help requests, which can cause the skill to activate outside its intended scope. In an agent ecosystem, overbroad activation can route sensitive or unrelated tasks into this skill unexpectedly, increasing the chance of incorrect actions, prompt collision, or privilege misuse through unintended invocation.
The top-level description says to use the skill whenever a user asks for broad categories like software-and-data, github, interact, cli, issue, or practical workflow support. That scope is so expansive that it effectively authorizes use across a large fraction of technical requests, increasing the chance of accidental invocation and allowing this skill to overshadow more appropriate or safer specialized skills.
The trigger keywords are extremely broad and map to common software-development language such as 'github', 'cli', 'api', 'issues', and 'run'. This can cause the skill to activate in many unrelated conversations, leading to inappropriate routing, unintended execution of the skill workflow, and increased exposure to prompt-scope abuse or irrelevant instructions.
The trigger sentence begins with a very broad everyday phrase ('Help me'), which can cause the skill to activate for many unrelated requests. In an agent environment, over-broad activation can route sensitive or irrelevant tasks into this skill unexpectedly, increasing the chance of unsafe actions, incorrect guidance, or prompt-surface expansion.
The trigger phrases are generic and broad enough to match many routine software or GitHub-related requests, which can cause unintended invocation of this skill in contexts the user did not explicitly request. In an agent ecosystem, overbroad activation increases the chance of inappropriate tool selection, accidental execution of workflows, and exposure of repository or issue-management actions to the wrong task context.
This file is explicitly a Chinese-language variant (README.zh-CN.md) but does not state that language selection is optional or explain why the locale is required. Under the policy, locale-specific behavior should either be opt-in or clearly justified as region-specific.
The example trigger sentences are generic requests for help or workflows and do not add meaningful constraints beyond everyday technical phrasing. This reinforces overbroad activation behavior by training selection systems or maintainers to treat ordinary requests as sufficient reason to invoke the skill.
The trigger keyword list includes very broad terms such as "run" and "api" alongside common development words like "github" and "issue", which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance the agent applies this workflow in the wrong context, leading to confused task routing, unintended actions, or disclosure of irrelevant repository/process guidance.
The example trigger phrases are highly generic requests like "Help me" and "I need a practical workflow" with only loosely attached demand text, so they do not establish clear boundaries for when this skill should be invoked. This can train routing or matching systems to over-select the skill for vague support requests, increasing accidental invocation and inappropriate handling of unrelated tasks.
The default prompt is extremely broad and uses generic terms like 'help me' and common workflow language, which can cause the skill to be selected in unrelated conversations. This increases the risk of unintended invocation, context capture, and user confusion, especially because the skill is positioned for broad software/GitHub-style assistance rather than a narrowly scoped task.
Enabling implicit invocation without clear trigger boundaries allows the skill to activate based on ambiguous user requests. In a broadly described developer-helper skill, this can lead to over-triggering across many normal software conversations, causing unintended tool routing and possible exposure of user context to a skill the user did not mean to invoke.
Although slightly more specific, the trigger sentence is still ambiguous because it centers on a generic request for 'a practical workflow' rather than a clearly bounded GitHub-related task. This makes accidental invocation plausible and could cause the skill to handle requests outside its intended safety and competence boundaries.
No suspicious patterns detected.
