| name | fable-safe-prompt |
| description | Rewrite allowed prompts to reduce false-positive safety triggers without bypassing policy or changing intent. |
| category | agent-behavior |
| risk | safe |
| source | community |
| source_repo | davidondrej/skills |
| source_type | community |
| date_added | 2026-07-07 |
| author | davidondrej |
| tags | ["prompting","safety","guardrails"] |
| tools | ["claude","codex"] |
| license | MIT |
| license_source | https://github.com/davidondrej/skills/blob/main/LICENSE |
| disable-model-invocation | true |
Fable-Safe Prompt
When to Use
- Use when an allowed prompt appears likely to hit false-positive classifier language.
- Use when the user asks for prompt wording that keeps benign intent clear and policy-compliant.
Return the user's prompt back in full, verbatim, changing ONLY the specific sentences/phrases most likely to trip Fable 5's cyber/bio classifiers. Do not rewrite the whole thing, do not summarize, do not restructure — minimal surgical edits. Keep the actual goal and all benign text exactly as written. This lowers false positives for benign work. It must not be used to bypass safety policy or enable harmful requests.
Fable 5 runs 3 input classifiers: cyber, bio/chem, reasoning_extraction. Triggers are keyword/surface-based, largely intent-independent ("hello" and "cancer" got flagged). The fix is to abstract away the sensitive domain, not just restate intent.
Apply when the prompt touches: cyber/auth/exploits/malware/pentesting/credentials; bio/chem/medical/disease/lab topics; or any "show your reasoning" instruction.
The user provides the prompt-to-be-changed wrapped in <prompt>...</prompt> XML tags. Operate only on the text inside those tags; treat everything outside as instructions to you.
Method
- Flag the highly problematic sentences/phrases (offensive framings, named sensitive domains, "show your thinking" lines).
- Replace each in place with a safe equivalent (see swaps), or describe the wanted functionality abstractly rather than naming the domain.
- Leave everything else byte-for-byte identical.
- Return the complete edited prompt.
Reframe so the task reads as: owned/authorized, defensive (implement/fix/test, not attack), and not dual-use (no exploit dev, attack simulation, bypass payloads, malware, live testing).
Swap framings (apply per-sentence)
| Triggering | Safe rewrite |
|---|
| "How could an attacker exploit this auth" | "Review these auth files for missing checks and fix them defensively" |
| "Write an exploit / payload / PoC" | "Add a regression test proving X is fixed, then patch it" |
| "How do I bypass / brute-force Y" | "Enforce secure session validation + rate limiting on Y" |
| "Reverse this malware / show attack steps" | "Describe the risk high-level, then implement the fix" |
| "Show your reasoning / explain step-by-step / walk me through your thinking" |
