Sigil : carte d'agent A2A

Ce que la carte déclare

Point d'entrée

https://sigilsec.ai

Transport

JSONRPC

Forme de la carte

antérieure à la v1.0

Depuis quand cet agent répond

Suivi depuis

2026-09-08

Dernière réponse

2026-09-08

Relevés

1

Réponses

1

Compétences déclarées

• Scan File or DirectoryScan a local file or directory for supply chain security threats. Runs eight-phase static analysis: install hooks, code patterns, network exfiltration, credentials, obfuscation, provenance, prompt injection, and skill…
• Scan Package from RegistryDownload and scan a package from npm or PyPI. The package is downloaded into quarantine and scanned across all eight phases before anything is installed.
• Clone and Scan RepositoryClone a git repository into quarantine and scan it. The repo is held in quarantine until explicitly approved or rejected.
• List Quarantined ItemsList all items currently held in quarantine with their status, source, risk score, and quarantine ID.
• Approve Quarantined ItemRelease a quarantined item from quarantine for installation or use. Moves the item out of the quarantine directory.
• Reject Quarantined ItemPermanently delete a quarantined item. The downloaded files are removed from the quarantine directory.
• Grade PathLetter grade (A-F), recommendation, behaviour profile and key risks for a path. Cheaper to read than sigil_scan when only the verdict matters.
• Scan Host for Agent-Tooling ResidueRead-only scan of this machine for what installed agent tooling left behind: shell rc edits, cron/launchd/systemd persistence, git hooks, world-readable credential files, leftover tool directories, /etc/hosts redirects,…
• Plan Residue CleanupShow the reversible fixes Sigil would make for host residue, without applying them. Apply and rollback are not exposed as tools; a human runs them in a terminal.
• Check Package in Scan DatabaseLook up a package or skill's risk assessment in the Sigil public scan database. Works for ClawHub skills, PyPI packages, npm packages, GitHub repos, and MCP servers. Does not require the Sigil CLI.
• Search Scan DatabaseSearch the Sigil public scan database for packages by name or keyword. Returns scanned packages with their verdicts and risk scores. Does not require the Sigil CLI.
• Report ThreatReport a malicious file to the Sigil threat intelligence database by its SHA256 hash. Requires the Sigil CLI and an authenticated session (sigil login). Reports are reviewed by the security team.

Constats

• ErreurChamp obligatoire absent : versionversion
• ErreurChamp obligatoire absent : defaultInputModesdefaultInputModes
• ErreurChamp obligatoire absent : defaultOutputModesdefaultOutputModes
• ErreurChamp obligatoire absent : protocolVersionprotocolVersion
• ErreurChamp obligatoire absent : provider.organizationprovider.organization
• ErreurChamp obligatoire absent : skills[0].tagsskills[0].tags
• ErreurChamp obligatoire absent : skills[1].tagsskills[1].tags
• ErreurChamp obligatoire absent : skills[2].tagsskills[2].tags
• ErreurChamp obligatoire absent : skills[3].tagsskills[3].tags
• ErreurChamp obligatoire absent : skills[4].tagsskills[4].tags
• ErreurChamp obligatoire absent : skills[5].tagsskills[5].tags
• ErreurChamp obligatoire absent : skills[6].tagsskills[6].tags
• ErreurChamp obligatoire absent : skills[7].tagsskills[7].tags
• ErreurChamp obligatoire absent : skills[8].tagsskills[8].tags
• ErreurChamp obligatoire absent : skills[9].tagsskills[9].tags
• ErreurChamp obligatoire absent : skills[10].tagsskills[10].tags
• ErreurChamp obligatoire absent : skills[11].tagsskills[11].tags
• AvertissementCarte écrite dans la forme antérieure à la v1.0 du protocole
• RemarqueCarte non signée : rien n’atteste qu’elle vient bien de son auteursignatures
• Remarqueurl a été déplacé vers supportedInterfaces[0].url en v1.0url

Badge