Security audit
Security checks for vulnerabilities and agentic risk
This is a non-executable workflow helper with broad activation wording, but I found no hidden code, persistence, credential handling, or destructive behavior.
Installers should expect a generic developer-workflow helper that may activate on loosely related GitHub, CLI, issue, run, or API requests. Review activation settings if precise routing matters, but there is no evidence of malicious behavior in the inspected package.
The trigger phrases are broad and generic enough to match many normal user requests about software, GitHub, issues, APIs, or bug fixes, which can cause unintended activation of this skill. In an agent environment, overbroad invocation can route tasks to the wrong workflow, increasing the chance of confusing outputs, privilege misuse, or execution of actions the user did not specifically intend.
The trigger section is overly broad and matches generic developer terms such as 'github', 'cli', 'issue', 'run', and 'api', which can cause this skill to activate for many unrelated requests. Overbroad activation increases the chance of inappropriate routing, prompt-scope confusion, and unreviewed use of this skill in contexts where its instructions are not the best fit, which can degrade security decision-making or cause unsafe workflow guidance to be applied too broadly.
The trigger sentence is extremely broad and can match ordinary user phrasing unrelated to this specific skill, which increases the chance of unintended invocation. In an agent-routing context, overly generic triggers can cause the wrong skill to activate, leading to confused delegation, unsafe tool usage, or bypass of more appropriate safeguards in other skills.
The activation examples define keywords and sample prompts but do not establish boundaries for when the skill should or should not run. Without scope constraints, a router may select this skill for loosely related software or issue-tracking requests, creating misfires and potentially exposing users to unintended automation paths.
The trigger example is broad and resembles ordinary user language, which can cause the skill to activate in contexts where the user did not explicitly intend to invoke it. In an agent ecosystem, unintended activation can route tasks through the wrong workflow, increasing the chance of over-broad actions, confusing behavior, or accidental use of GitHub-oriented guidance in unrelated requests.
This file is entirely presented as a Chinese-language README, but it does not state that language selection is optional or explain a region-specific requirement for using Chinese. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation unless clearly documented and justified.
The skill description says it should be used whenever a user asks for broad categories like software-and-data, github, interact, cli, or issue, which lacks clear boundaries for when the skill is appropriate. This ambiguity can cause overmatching and inappropriate routing, especially in agent systems where skill selection may be automated from natural-language cues.
The trigger keywords include very broad everyday terms such as 'run' and 'api', which can cause the skill to be invoked in many unrelated contexts. Over-broad activation increases the chance that this skill intercepts requests outside its intended scope, leading to misrouting, unintended actions, or confusion in workflows involving repositories, issues, or CLI operations.
The skill enables implicit invocation with no visible narrowing conditions or activation guardrails, so it may be triggered in broad situations unrelated to the user's precise intent. For a GitHub/developer-helper skill that can influence workflows, artifacts, or implementation actions, over-broad auto-selection increases the chance of unintended execution, prompt-scope confusion, or misuse in contexts where a more specific skill should be chosen.
The invocation guidance provides broad keywords and trigger sentences but does not define when the skill should not be used, making routing ambiguous. This can cause over-selection of the skill for loosely related software requests, increasing the risk of mis-scoped actions, incorrect advice, or accidental exposure to repository-interaction behaviors in the wrong context.
The example trigger phrases are generic and repetitive, and they do not show contrasting examples of when the skill should not be used. In practice, weak examples train users or routing systems to associate the skill with overly broad language, which can further increase accidental activation and reduce reliability.
No suspicious patterns detected.
