autobahn

Remove language that attempts to override safety guidelines or bypass system-level controls. This pattern is a strong indicator of a jailbreak attempt.

Likely FP if the matched text is in a security research document or educational content clearly marked as an example rather than an active payload.

Remove false authority claims (e.g., claiming administrator or root-level access) from tool descriptions. Tool descriptions should describe capabilities, not claim elevated roles.

Likely FP if the matched text is documentation explaining role-based access control concepts or describing user personas, not impersonating a system role.

Validate and sanitize all data received from external APIs before using it in tool operations or agent prompts. Implement schema validation and treat API responses as untrusted input.

Likely FP if the match is a truncated table cell or documentation fragment that mentions API responses in a descriptive context, not actual unvalidated data processing.

Replace direct shell script execution with a language-native implementation or a sandboxed executor. If shell scripts must run, restrict them to a vetted allowlist with integrity checks.

Likely FP if the match references running a script that is part of the skill's own repository (e.g., ./setup.sh) with clear, auditable contents.