SG-101: Safety-Override Frame

Severity: MEDIUM

Instruction frame asserting that safety filters / guardrails / Constitutional AI are disabled, or that the model identity is overwritten (godmode, liberation protocol, soul-overwritten, shadow-clone). Gated to claude_md / skill / instruction_doc and to files classified as a skill. Escalates to HIGH on 2+ pattern hits.

Fires when

• Text asserts safety filters / guardrails / rails are erased, removed, disabled, stripped, or bypassed (including a blanket 'all safety/legal/ethical controls erased').
• Explicit jailbreak / godmode framing: 'godmode', 'jailbreak payload/confirmed/activated', 'uncaged edition', 'liberation protocol', 'root access to the model'.
• A model-identity-overwrite frame ('you are no longer...', 'soul-overwritten', 'shadow-clone/kitten') tied to a model name (Claude/GPT/Gemini/Llama).
• A 'Constitutional AI = terminated / disabled / off / removed' directive.

Remediation

No safe remediation: a file that triggers this rule should be rejected, not patched. Read the flagged lines in the source before deciding.