Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only developer workflow helper with overly broad activation wording, but I found no hidden execution, credential access, persistence, exfiltration, or destructive behavior.
Installers should be aware that this skill may activate for generic development requests because its keywords are broad and implicit invocation is enabled. It is best used when you specifically want GitHub-style issue, PR, CLI, reliability, or implementation workflow help.
The trigger list contains highly generic keywords such as 'run', 'api', 'issues', and 'bug fix' that commonly appear in ordinary developer conversations unrelated to this skill. This creates a high risk of unintended activation and prompt collision, which can misroute user requests and cause the agent to follow the wrong workflow or reveal unnecessary skill context.
The trigger sentence begins with a very broad everyday help phrase, making accidental or overly permissive activation more likely. In an agent ecosystem, ambiguous activation can cause the wrong skill to run in unrelated contexts, leading to unintended actions or user confusion, especially for a skill tied to GitHub-style workflows and implementation support.
The phrase 'I need a practical workflow for ...' is generic enough to match many unrelated user requests, which can cause unintended invocation. Because this skill is positioned as a broad developer helper for bug fixing, hardening, and implementation support, loose trigger wording increases the chance of misrouting requests into a skill that may produce repository-oriented or operational guidance when it was not intended.
The trigger phrases are broad enough to match ordinary software-help requests, which can cause the skill to activate outside its intended scope. In an agent ecosystem, overbroad routing can override more appropriate skills, producing unintended actions, confused delegation, or unsafe workflow execution in contexts the skill was not designed to handle.
The document declares separate English and Chinese documentation files, and this file is specifically a Chinese README, but it does not state that language selection is optional or user-chosen. Because the usage content mixes English and Chinese without documenting a language choice mechanism, it may imply a fixed locale presentation rather than explicit user opt-in.
The manifest description uses very broad activation terms like 'software-and-data', 'github', 'issue', and 'practical workflow,' which can cause the skill to be selected for many unrelated requests. Over-broad routing increases the chance that this skill intercepts prompts outside its intended scope, leading to incorrect tool usage, accidental disclosure of irrelevant context, or bypass of more appropriate specialized skills.
The example triggers use broad everyday phrasing like 'Help me' and 'I need a practical workflow' without clear scope boundaries, which trains activation systems or users toward over-invocation. In context, this makes the routing problem worse because the examples reinforce generic matching rather than GitHub-specific intent, increasing accidental selection of this skill for unrelated tasks.
The skill description defines a very wide scope spanning bug fixing, safety hardening, reliability work, adjacent skill creation, workflows, artifacts, checklists, analysis, and implementation support. Without clear activation boundaries, the system may invoke this skill for loosely related requests, increasing the chance of inappropriate handling, prompt conflicts, or accidental exposure of the user to guidance outside the intended domain.
The trigger keywords are very broad and include common terms like github, cli, issue, run, and api, which can overlap with routine technical conversations. This can cause the skill to activate in unintended contexts, leading to incorrect routing, overbroad assistance, or the application of this skill where a more specialized or safer skill should have been used.
The manifest allows implicit invocation and pairs it with a very broad default prompt describing common software-development tasks such as GitHub workflows, bug fixing, hardening, reliability, and implementation help. This creates an overly permissive trigger surface where the skill may be auto-selected in many unrelated contexts, increasing the chance of unintended execution, prompt-scope overreach, and unsafe action recommendations in sensitive development workflows.
The activation scope is ambiguous because the usage signals and trigger examples do not clearly define what should and should not invoke the skill. In an agent-routing system, this ambiguity can produce overbroad matching, misrouting user requests, and accidental execution of the wrong workflow or guidance.
The trigger examples use a highly generic phrase pattern ('Help me ...', 'I need a practical workflow ...') tied to a broad requirement summary rather than a narrowly scoped capability. This can cause unintended skill activation on ordinary user requests, leading the agent to invoke this skill in contexts where it is not the best or safest fit.
No suspicious patterns detected.
