Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only GitHub/developer workflow helper with overly broad routing language, but no hidden execution, credential access, persistence, or destructive behavior was found.
Install only if you want a general developer-workflow helper. Because implicit invocation is enabled and the triggers are broad, users should watch for accidental activation on unrelated coding requests and prefer tighter trigger wording in future versions.
The skill description uses very broad activation terms like 'software-and-data', 'github', 'interact', 'cli', 'issue', and generic requests for workflows or analysis. In an agentic routing system, this can cause the skill to be selected for many unrelated prompts, increasing the chance of inappropriate tool use, misleading outputs, or bypass of more narrowly scoped safer skills.
The keyword list includes highly generic terms such as 'run', 'api', 'issues', and 'bug fix', which are common across many software requests. This makes unintended invocation likely, and in multi-skill environments can route users into a broader-than-intended workflow that may act on repositories, issues, or CLI-related tasks without sufficient relevance checks.
The trigger sentence is so broad and generic that it could match ordinary user requests unrelated to this skill, causing unintended invocation. In an agent environment, overbroad routing can expose users to the wrong workflow, create confusing autonomous actions, and increase the chance that downstream tools are used in an unintended context.
The Usage section provides malformed and low-specificity invocation examples, making the skill's activation scope unclear. This ambiguity can cause misrouting by upstream agents or users, resulting in the skill being selected for tasks it was not designed to handle, which is especially risky for a developer-helper skill that may influence code, repository, or issue workflows.
The trigger phrase is overly broad and written in everyday language, which can cause accidental activation outside the intended Github-style workflow context. In an agent ecosystem, ambiguous triggers increase the chance that the skill is invoked on unrelated requests, leading to unintended actions, incorrect tool selection, or unsafe workflow execution.
The trigger phrases are broad and partially generic, which can cause the skill to activate in situations outside its intended scope. In an agent ecosystem, ambiguous activation can lead to accidental invocation, inappropriate handling of unrelated requests, and unsafe workflow substitution for tasks the skill was not meant to perform.
The file presents itself as the Chinese user documentation and references Chinese and English variants, but the content here does not state that language selection is optional or user-driven. For a general-purpose GitHub workflow helper, imposing a specific language/locale in the skill experience without opt-in can violate language choice policy.
The example trigger sentences are broad, natural-language prompts that mirror everyday help requests without meaningful scope boundaries. Examples often shape routing behavior and prompt authorship, so vague examples can normalize over-triggering and cause the skill to be invoked outside its intended GitHub-specific use case.
The trigger keyword list includes very generic terms such as 'github', 'cli', 'issue', 'run', and 'api', which are common across many unrelated user requests. This can cause the skill to activate outside its intended scope, leading to incorrect routing, user confusion, and unintended execution of workflows or guidance in contexts where this skill is not appropriate.
The example trigger phrases are broad, incomplete, and closely resemble ordinary help requests, so they do not establish clear activation boundaries. Because these examples effectively teach the router to associate common support language with this skill, the skill may be invoked for generic development questions that do not actually match its intended purpose.
The skill enables implicit invocation while advertising a very broad, everyday-language purpose covering generic software, GitHub, CLI, issues, workflows, artifacts, checklists, analysis, and implementation support. This can cause the agent to auto-select the skill in loosely related conversations, expanding its activation surface and increasing the chance of unintended execution, overreach, or misuse in sensitive development contexts.
The trigger guidance does not define clear boundaries for when the skill should and should not be used, which makes misrouting more likely. Without scope constraints and negative examples, a dispatcher or agent may invoke this skill for loosely related software tasks, reducing safety and reliability and potentially chaining into inappropriate actions.
No suspicious patterns detected.
