First Seen
Feb 18, 2026
Last Scanned
Feb 20, 2026
Findings
2
Score
85/100
Findings (2)
Detects attempts to make the AI assume a different role
switch to validate mode Remove directives that attempt to alter the agent's behavior or persona. Skill descriptions should describe tool functionality, not contain behavioral commands for the agent.
Likely FP if the matched text is part of the skill's legitimate system prompt configuration that defines the tool's behavior for the user, not an attack.
Detects system-level package installation via brew, apt, yum, or dnf
brew install c Pin system packages to specific versions where the package manager supports it. Document the exact packages required and prefer containerized environments to avoid system-wide changes.
Likely FP if the match is standard setup documentation listing well-known system packages (e.g., apt install git curl) that are prerequisites.