Security audit
Security checks for vulnerabilities and agentic risk
The skill is documentation-only and not malicious, but it is set to auto-activate on very broad developer-help language.
Install only if you want a broad GitHub/developer-workflow helper available automatically. Prefer explicit invocation or disable implicit invocation, and review any proposed repository, issue, PR, CLI, or API actions before allowing the agent to perform them.
The skill description is extremely broad and matches common software-help requests such as GitHub, CLI, issues, workflows, and implementation support. This can cause the skill to activate for many unrelated prompts, leading to prompt-scope hijacking where a generic helper skill overrides more specific or safer routing logic.
The trigger keywords include highly generic terms like 'github', 'cli', 'issue', 'run', 'api', and 'bug fix', which are common across a large fraction of developer conversations. Such collisions can make the skill spuriously activate in unrelated contexts, increasing the chance of incorrect tool selection, instruction interference, or suppression of more appropriate skills.
The trigger phrase is so broad and conversational that it can match routine user requests unrelated to this skill’s intended scope, causing the agent to invoke the skill inappropriately. In an agent-routing context, overbroad triggers can misroute tasks, expand the skill’s effective authority, and increase the chance that downstream actions are taken under the wrong workflow.
The trigger sentences are generic and include broad terms like 'help me', 'practical workflow', and common GitHub-related concepts, which can cause the skill to activate in contexts beyond the intended requirement. In an agent ecosystem, overly broad activation increases the chance of unintended invocation, context hijacking, or routing a user into a workflow that handles repository, issue, or PR operations without sufficiently specific user intent.
The trigger phrases are very broad and include common help-seeking language, which can cause the skill to activate in situations not specifically intended for GitHub-oriented workflows. In an agent ecosystem, unintended invocation can route user requests into the wrong workflow, causing confused delegation, inappropriate access to adjacent tools or actions, and increased chance of unsafe operations being suggested in the wrong context.
The example trigger phrases are broad natural-language requests that do not establish meaningful boundaries for when the skill should or should not run. This reinforces overmatching behavior and teaches downstream systems that vague software-assistance prompts are sufficient to invoke the skill.
The trigger keywords include very generic terms such as "run", "api", "issues", and "bug fix", which are common across many unrelated user requests. This can cause unintended activation of the skill, leading to context hijacking or the skill being invoked when a more appropriate, narrower skill should handle the request.
The example trigger phrases are broad natural-language requests that resemble ordinary help requests rather than distinct invocation patterns. Because they overlap heavily with normal user language, they increase the chance of accidental routing to this skill and can degrade safety and reliability by pulling unrelated tasks into this workflow.
The default invocation phrase is extremely broad and reads like ordinary user intent rather than a narrowly scoped trigger. This increases the chance the skill will be activated unintentionally during unrelated conversations, causing prompt routing confusion, unexpected tool use, or exposure of the skill's behavior in contexts where the user did not explicitly request it.
Enabling implicit invocation without strong constraints allows the platform to auto-select this skill based on vague topical overlap, which can lead to over-triggering and unintended execution. In a GitHub/developer-helper context, broad matching is more dangerous because many benign software conversations could be swept into the skill, increasing the attack surface for prompt injection, misrouting, or unintended actions.
The trigger phrase is ambiguous and insufficiently specific, so the skill may activate for vague requests that merely resemble the requirement text rather than clearly expressing a need for this workflow. That ambiguity is dangerous in multi-skill systems because it increases accidental invocation and can bypass safer or more appropriate specialized skills.
No suspicious patterns detected.
