Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with no executable payload, persistence, credential handling, or hidden data access, though its activation wording is overly broad.
Before installing, be aware that this skill may be selected for generic search or workflow requests more often than intended. It is best treated as a benign helper, but the publisher should narrow the trigger phrases and improve the Chinese localization for predictable use.
The trigger phrases are broad and include generic terms like "multi", "search", and common request forms that can match ordinary user speech, causing the skill to activate outside its intended scope. In an agent environment, overbroad activation can route unrelated tasks into this workflow, leading to unintended tool use, misleading outputs, or reduced safety by bypassing more appropriate skills.
The manifest description says to use the skill when a user asks for broad categories like "work-productivity" or "needs a practical workflow, artifact, checklist, analysis, or implementation support," which are common across many benign requests. This creates ambiguous routing conditions that can over-select this skill, leading to unintended invocation and reducing reliability and predictability of the agent system.
The trigger list includes very generic terms such as "multi," "search," "engine," and "bug fix," which can match many unrelated user requests and cause accidental skill activation. Over-broad invocation increases the chance that the skill runs in contexts it was not intended for, potentially interfering with routing, producing irrelevant guidance, or shadowing more appropriate skills.
The trigger list includes very generic words such as "multi", "search", and "engine", which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance that this skill unexpectedly takes over a task, injects irrelevant workflow guidance, or interferes with routing to a more appropriate skill.
The trigger sentence is so generic that it can match ordinary user requests unrelated to this skill, causing the system to invoke the skill in contexts the user did not intend. Over-broad activation increases prompt-routing errors and can expose users to irrelevant workflow instructions, unintended tool use, or policy/scope bypass if the skill is selected too often.
The trigger phrases are broad, repetitive, and include generic terms like "multi," "search," and "engine," which can cause the skill to activate outside its intended context. In an agent ecosystem, unintended invocation can route user requests into the wrong workflow, leading to irrelevant actions, reduced reliability, and possible unsafe behavior if the skill performs consequential guidance based on a mistaken match.
This Chinese-language README includes core descriptive and operational text in English, which effectively imposes a language choice on users without opt-in or explanation. The policy requires offering a language/locale choice or clearly documenting and justifying locale constraints.
The example trigger sentences normalize vague prompts like "Help me" and "I need a practical workflow," which trains or encourages broad matching behavior beyond the intended scope. While examples alone are not executable logic, they reinforce an unsafe activation pattern and can contribute to accidental invocation in real use.
The description says the skill should be used when users mention broad categories like work-productivity, multi, search, or engine, but it does not clearly define when the skill should not activate. This ambiguity can produce accidental invocation and misrouting, especially because the skill is framed as broadly applicable to workflows, checklists, analysis, and implementation support.
The default prompt uses broad, everyday language such as 'help me' and generic productivity/search terms, which can cause unintended or implicit invocation in contexts unrelated to this specific skill. Because implicit invocation is enabled, this increases the chance the agent routes ordinary user requests into this skill unexpectedly, expanding attack surface and creating opportunities for prompt hijacking or misuse through accidental activation.
Although this trigger adds slight context, it still contains broadly phrased language that could match many normal requests for a "practical workflow." Ambiguous routing conditions can misfire frequently in agent environments, leading to inappropriate skill execution and reducing trust, reliability, and safety of downstream behavior.
The file lists separate English and Chinese instruction and guide files, but it does not state how the user's preferred language is selected or that language choice is optional. This can create an implicit language/locale constraint without clear user opt-in.
