copropriete@r1
VERIFIED· install onlyPublisher claims: "Enables an assistant to search French co-ownership law (the 1965 statute and 1967 decree) for the articles that answer a question, returning references, excerpts, Légifrance links, and an explicit refusal when the texts don't cover it, and to read an article's full official text with its entry-into-force and consolidation dates." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
ANTHROPIC_API_KEYDATABASE_URLConfiguration, not credentials: DIMENSION, DOSSIER_CORPUS, DOSSIER_MODELE, DOSSIER_RECLASSEUR, FICHIER_VECTEURS, INGESTION_AU_DEMARRAGE, LEXIQUE, MAJORITES, MODELE_CLAUDE, MODELE_HF, MODELE_REVISION, PLANCHER_ARTICLE_CITE, POIDS_PLEIN_TEXTE, POOLING, PREFIXES, RECLASSEUR, RECLASSEUR_CANDIDATS, RECLASSEUR_PAR_POINT, SEUIL_SIMILARITE, TAILLE_MAX_MORCEAU- Where it talks to
- no vendor host named in the codeAlso gouv.fr — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names gouv.fr as well as its own vendor. The guard injects ANTHROPIC_API_KEY, DATABASE_URL only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is copropriete@r1 safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-13 and scored it 89/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
# Facultatif : la réponse rédigée par Claude n'est activée que si la clé est fournie (fichier .env).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.&& rm -rf /root/.cache/huggingface /modeles/mmarco/.cacheFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.&& rm -rf /root/.cache/huggingface /modeles/bge-m3/.cacheFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.