Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only helper skill for GitHub-style development workflows, with no executable payload or hidden persistence, though its activation wording is overly broad.
Install only if you want a broad GitHub-style development workflow helper. Treat its suggestions as advisory, and confirm before letting an agent run CLI commands, change repositories, or interact with issues, PRs, or APIs.
The skill description and usage guidance are broad enough to match many ordinary software-support requests, which increases the chance of unintended or silent invocation. Over-broad activation can route users into the wrong workflow, causing incorrect actions, context leakage across tasks, or unsafe automation in situations where the user did not explicitly request this skill.
The keyword list contains highly generic terms such as 'run', 'api', 'issue', and 'cli' that commonly appear in unrelated technical conversations. In agent ecosystems, such collisions materially raise the risk of accidental skill activation, which can override more appropriate skills or cause the agent to take GitHub-oriented actions based on weak signals.
The trigger sentence is so broad and generic that it can cause the skill to activate for loosely related everyday requests rather than clearly scoped GitHub-style workflow tasks. Over-broad invocation increases the chance of unintended routing, where users may receive this skill in contexts it was not designed for, leading to irrelevant actions, unsafe assumptions, or bypass of more appropriate safeguards in narrower skills.
The trigger examples are generic and broad enough that the skill may activate for loosely related requests, increasing the chance of unintended invocation in contexts involving GitHub, CLI, issues, or bug-fixing. In a skill that may guide repository or API-affecting workflows, accidental activation can lead to overreach, inappropriate advice, or actions being suggested without sufficient user intent confirmation.
The trigger phrases are broad enough to match common user requests such as asking for help, practical workflows, or implementation support, which can cause the skill to activate outside its intended scope. In an agent ecosystem, overscoped routing can misdirect tasks into a Github-interaction workflow that may encourage unnecessary repository, CLI, or issue-management actions on unrelated prompts.
The example triggers repeat vague requirement text and do not show clear activation boundaries, which trains invocation systems or maintainers toward permissive matching behavior. Because the examples fail to distinguish explicit GitHub-interaction tasks from general development help, they reinforce the risk of misrouting and unintended execution.
The trigger keywords are overly broad and include common terms like github, cli, run, api, issues, and bug fix, which can match many unrelated technical conversations. This can cause the skill to activate outside its intended scope, leading to misrouting, confusing responses, or unintended execution of workflows in contexts where a more appropriate skill should handle the request.
The sample trigger phrases are generic requests for help or a practical workflow and do not define boundaries for when the skill should not activate. In a routing system, such examples can reinforce overbroad matching behavior, increasing the chance that unrelated user requests are captured by this skill and receive mismatched guidance.
The skill enables implicit invocation while providing a very broad description and default prompt, which can cause the agent to trigger this skill in situations that only loosely match the user's intent. This creates an authorization and scope-control problem: the skill may be invoked unexpectedly in unrelated conversations, increasing the chance of unintended repository, CLI, or workflow actions based on ambiguous context.
The invocation guidance does not define clear boundaries for when the skill should and should not be used, and the listed keywords are expansive enough to match many unrelated software requests. This ambiguity can cause over-invocation across general development tasks, increasing misclassification risk and making it easier for an agent to select this skill outside its intended safety and capability envelope.
The README promotes GitHub-style workflows but does not warn users that such workflows may involve repository changes, issue/PR operations, CLI usage, or API interactions. In this context, missing safety boundaries can cause users to assume the skill is read-only or low-risk, which increases the likelihood of unsafe execution or unintended external side effects.
The file lists separate English and Chinese instruction/readme files, but the README itself does not state how the user's preferred language is selected. This can create a locale-policy concern if the skill defaults to a specific language without explicit user opt-in.
This README is entirely in Chinese and does not state that the skill is region-specific or provide user opt-in for language selection. Under the policy, forcing a specific language without choice can be a natural-language policy concern unless the locale restriction is clearly justified.
No suspicious patterns detected.
