Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward LaTeX document template helper with no executable payload, network behavior, persistence, or sensitive access.
Installers should understand that this skill is meant for LaTeX academic documents and may default toward English; explicitly request another language or a non-LaTeX writing workflow when needed.
Mandating English-language support as the primary mode without user choice can cause inappropriate handling of non-English requests and may lead the agent to ignore user intent or transform content unnecessarily. This is not a classic code-execution issue, but it is a trust and policy weakness because the skill imposes a hidden behavioral constraint on outputs.
The trigger phrases are generic enough to match ordinary user requests such as 'write a paper' or 'create a LaTeX document,' which can cause the skill to activate outside a narrowly intended context. Over-broad activation increases the chance of misrouting benign requests into this skill and may bypass better-suited tooling or policy checks tied to more specific workflows.
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.
permit persons to whom the Software is furnished to do so.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE
FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
Reinforcing English-focused output in the notes further cements a hidden constraint that may conflict with user expectations and lead to systematic mishandling of multilingual requests. In context, this makes the issue slightly more likely to affect behavior because it appears both in the main description and in implementation notes.
No suspicious patterns detected.