Ae4
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
Suspicious Unicode normalization or mixed-script content
- Content
Security audit
Security checks for vulnerabilities and agentic risk
This is a pure instruction-based monitor buying guide with no code execution, persistence, or credential access, though users should note it does include named product suggestions despite claiming to be brand-neutral.
Install this only if you want the agent to guide monitor purchases and potentially name specific models. Treat product suggestions as research starting points, verify current specs, prices, warranty, and availability yourself, and be aware that the skill asks for location and hardware details to tailor advice.
Suspicious Unicode normalization or mixed-script content
The manifest markets the skill as brand-neutral, but the instructions later require recommending specific real monitor models by region. This creates a policy-integrity mismatch that can mislead users about neutrality and opens the door to covert product steering, affiliate-style influence, or undisclosed commercial bias under the guise of impartial advice.
The skill explicitly says it will not recommend specific brands, then later mandates suggesting real products and models. Contradictory instructions like this can be exploited to mask promotional behavior, confuse auditors, and erode user trust because the user is told the consultation is independent while the workflow ultimately steers them toward named products.
This markdown file includes activation examples such as "help me choose a monitor" and "best monitor for me," which are broad natural-language phrases rather than tightly scoped invocation triggers. Although the surrounding section provides some scope and negative examples, these phrases remain vague enough to match routine conversation and could cause unintended skill activation in systems that rely on phrase matching.