Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad activation wording, but no hidden code, persistence, or data access.
This skill is reasonable to install for skill-vetting workflow help. Review its implicit invocation setting and broad trigger words if you want to avoid it activating on generic security, GitHub, or bug-fix requests.
The trigger sentence is broad enough to match ordinary requests about security, GitHub, bug fixes, or general workflow help, which can cause the skill to activate outside its intended scope. In an agent ecosystem, overbroad activation can route sensitive or unrelated tasks into the wrong skill, leading to unsafe automation, incorrect guidance, or unintended handling of security-relevant requests.
The manifest description says to use the skill when a user asks for broad categories like "security," "first," or any practical workflow or checklist, which creates an ambiguous activation condition. In a multi-skill environment, this can over-match benign requests and route users into an unrelated skill, reducing reliability and potentially overriding safer or more specialized handling.
The trigger keyword list includes very broad terms such as "security," "first," "before," and "github," which are common in ordinary conversation. This can cause accidental invocation in unrelated contexts, leading to prompt-scope confusion, unexpected workflow steering, or interference with other more appropriate skills.
The trigger list includes very common words such as 'security', 'first', 'before', 'github', and 'bug fix', which are likely to appear in many unrelated user requests. This can cause the skill to activate unexpectedly, leading to incorrect routing, over-broad interception of conversations, and increased chance that users receive workflow-specific guidance when they did not intend to invoke this skill.
The trigger sentences are overly generic and include common words like "help me," "practical workflow," "security," and "github," which can cause the skill to activate outside its intended scope. In an agent environment, broad activation increases the chance of unintended routing, context hijacking, or this skill preempting more appropriate specialized skills, especially for security-sensitive requests.
The activation guidance does not clearly define when this skill should or should not be invoked, so overlapping requests may be ambiguously captured by this skill instead of a more appropriate one. Because this skill presents itself as a helper for vetting, security, reliability, and adjacent workflows, ambiguous scope increases the risk of misrouting user intent and producing misleading or over-authoritative outputs in security-sensitive contexts.
The trigger keywords and example phrases are broad enough to match common security and productivity requests such as 'security', 'first', 'github', or 'bug fix', which can cause the skill to activate when the user did not explicitly intend to invoke it. Unintended invocation can route sensitive or unrelated tasks through this workflow, increasing the chance of incorrect handling, prompt interference, or misuse of the skill in contexts where it is not appropriate.
The example trigger phrases are incomplete and highly generic, so they do not establish clear boundaries for when this skill should activate. Vague examples reinforce over-broad matching behavior and make accidental triggering more likely, especially because the skill is framed around common productivity and security language.
The description says to use the skill when a user asks for broad topics like work-productivity, security, or practical support, but does not define clear boundaries for activation. Ambiguous routing conditions increase the risk of unintended invocation and misclassification, especially because the skill overlaps with many general support, security, and productivity requests.
The default prompt includes very broad natural-language trigger terms like 'help me' and generic work/security phrasing, which can cause the skill to activate in many unrelated conversations. Because implicit invocation is enabled, this increases the chance of unintentional routing, prompt interference, or accidental use of this skill in contexts where the user did not explicitly request it.
SQP-3 applies to all file types and covers language/locale policy issues. In this Chinese README, core descriptive and trigger text remains in English, which can effectively force a language choice on users of the localized document without explicit opt-in or an offered preference.
