veilleur@0.1.0
VERIFIED· not startedPublisher claims: "Enables a local AI client to manage a Discord server through a bot: creating, editing and deleting channels, categories and roles, managing permissions, member roles, nicknames and timeouts, and sending messages and embeds. Each prepared plan must be approved in a local window before execution, and the server structure is backed up beforehand so changes can be rolled back." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Not started: dependency install failed; the server itself was not observed.- Tested
- the dependency install step · every file read, file written and host contacted by what ran
- Not tested
- server startup · the tool list · tool behavior
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
DISCORD_BOT_TOKENConfiguration, not credentials: DISCORD_GUILD_ID, VEILLEUR_HOME- Where it talks to
- no vendor host named in the codeAlso discord.com — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- no credential files read · no network
- What we could not test
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names discord.com as well as its own vendor. The guard injects DISCORD_BOT_TOKEN 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 [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-13 and scored it 82/100 (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 · 2 scenarios · 0 deviationsStatic findings
raise ValueError("Définis DISCORD_BOT_TOKEN ou renseigne-le dans .env")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Le projet se trouve dans ce dossier. Le token est dans `.env` : ne jamais lire son contenu dans un outil qui l'affiche, le journaliser ni le copier dans un message.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.(root / ".env").write_text("DISCORD_BOT_TOKEN=old\n", encoding="utf-8")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.5. Enable Developer Mode in Discord, right-click your server, and copy its ID.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.(root / ".env").write_text("DISCORD_BOT_TOKEN=fake\n", encoding="utf-8")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.subprocess.Popen([str(python), "-m", "veilleur.approve", plan_id], cwd=ROOT,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.5. Enable Developer Mode in Discord, right-click your server, and copy its ID.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.5. Enable Developer Mode in Discord, right-click your server, and copy its ID.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.load_dotenv(root / ".env", override=False)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.