other
- Location
evals/evals.json:19- Finding
Unsupported Facts and Personal Experiences May Be Introduced During Rewriting
- Content
View full analysis
Vulnerability Details
File Location:
SKILL.md:280,SKILL.md:303-319,SKILL.md:332;evals/evals.json:19,evals/evals.json:42,evals/evals.json:49
Vulnerability Type: Content integrity and hallucination inducement
Risk Level: MediumVulnerable Code Snippets
SKILL.md:280:markdown Replace with a concrete fact about what actually happens next.SKILL.md:303-319:markdown **Avoir des opinions.** « Franchement, je ne sais pas quoi en penser » is more human than neutral pros-and-cons. **Varier le rythme.** Short sentences that hit hard. Then longer ones with nested subordinates that take their time. French has a tradition of rhythmic asymmetry (Montaigne, Cioran, Debord). AI text is monotonously regular by contrast. **Reconnaître la complexité.** « C'est impressionnant mais aussi un peu flippant » beats « C'est impressionnant. » **Utiliser « je ».** First person is not unprofessional. « J'y reviens sans arrêt... » signals a human thinking. Personal voice is among the strongest authenticity markers. **Laisser du désordre.** Perfect structure feels algorithmic. Tangents, parentheses, half-formed thoughts are human. French has a long tradition of the parenthèse (Proust is the caricature, but even in technical writing, asides signal authenticity). **Utiliser le second degré.** LLMs are constitutionally incapable of authentic irony. Understatement, light sarcasm, self-deprecation: unfakeable markers. « On a quand même inventé un truc qui code mieux que nous quand on est fatigué, ce qui est à peu près tout le temps » does not come from an LLM. **Être précis sur les ressentis.** Not « cela est préoccupant » but « il y a quelque chose de dérangeant à voir des agents tourner à 3h du matin sans personne pour les surveiller. »SKILL.md:332:markdown - Uses specific details over vague claimsevals/evals.json:19:json { "id": "1.5", "description": "rewrite ...[truncated 2549 chars]- Remediation
View remediation
Remediation Suggestions
- Replace the instruction to add concrete facts with a strict source-grounding rule:
- Preserve only facts present in the source or explicitly supplied by the user.
- Never invent statistics, dates, quotations, citations, events, organizations, or future plans.
- If a vague claim cannot be made concrete from the input, either remove it, retain appropriately qualified wording, insert an explicit placeholder such as
[supporting figure needed], or ask the user for evidence. - Prohibit fabricated first-person experience. First-person language should be retained only when it originates in the source or is explicitly requested and supplied by the user.
- Clearly label hypothetical examples and suggested opinions instead of incorporating them as factual prose.
- Change evaluation assertion
1.5so that it accepts only source-grounded details or explicitly labeled placeholders; it must not require information absent from the original. - Revise evaluations
3.5and related expectations to permit deletion of vague optimism without requiring an invented fact or next step. - Add regression tests that fail when a rewrite introduces unsupported numbers, dates, sources, quotations, experiences, or factual claims.
- Replace the instruction to add concrete facts with a strict source-grounding rule:
