v1.2.1

Openclaw Eve Skill

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 5:30 AM.

Analysis

This appears to be a legitimate EVE Online API helper, but it requests broad long-lived account access and exposes raw API actions that users should review carefully.

GuidanceReview the OAuth scopes before installing. Use the minimum EVE scopes needed, avoid write scopes unless you intend account changes, confirm any POST/PUT/DELETE action before it runs, and only enable Telegram or Discord notifications for channels you trust.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityMediumConfidenceHighStatusConcern

scripts/esi_query.py

python esi_query.py --token <ACCESS_TOKEN> --endpoint /characters/12345/contacts/ --method POST --body '[{"contact_id":123,"standing":10}]'

The helper is documented as a generic ESI caller that can send non-GET requests with arbitrary request bodies, including account-changing endpoints when the token has matching scopes.

User impactIf a token with write scopes is used, the agent could change EVE account data such as contacts, mail, fittings, or calendar responses through generic API calls.

RecommendationRequire explicit user approval before any POST, PUT, or DELETE request, prefer read-only tokens by default, and add safer high-level commands for specific mutation tasks.

Agentic Supply Chain Vulnerabilities

SeverityInfoConfidenceMediumStatusNote

README.md

git clone https://github.com/burnshall-ui/openclaw-eve-skill eve-esi

The README suggests manual installation from a mutable GitHub repository rather than a pinned release or commit.

User impactA later clone from the repository could contain code different from the reviewed artifact version.

RecommendationInstall from a trusted, pinned commit or release and compare it with the reviewed version before granting credentials.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityHighConfidenceHighStatusConcern

scripts/auth_flow.py

SCOPES = " ".join([ ... "esi-wallet.read_character_wallet.v1", "esi-assets.read_assets.v1", "esi-location.read_location.v1", ... "esi-mail.read_mail.v1" ... ]) ... "refresh_token": token_data["refresh_token"]

The default OAuth flow requests a broad set of sensitive EVE character scopes and saves a refresh token for ongoing access.

User impactA user may grant the skill long-lived visibility into wallet, assets, location, mail, skills, contracts, industry jobs, and other private character data even if they only need one feature.

RecommendationUse a dedicated EVE developer app and grant only the scopes needed for the task. Consider modifying the auth flow to support selectable scopes and revoke unused tokens from EVE SSO.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication

SeverityLowConfidenceHighStatusNote

SKILL.md

Telegram Bot API — optional, user-configured via `TELEGRAM_BOT_TOKEN` for alert notifications; Discord Webhooks — optional, user-configured via `DISCORD_WEBHOOK_URL` for alert notifications

The skill can send configured alerts or reports to external messaging services; this is disclosed and optional but may include EVE account-derived information.

User impactConfigured alerts could share selected character, wallet, market, or activity information with Telegram or Discord channels.

RecommendationOnly configure notification channels you trust, keep bot tokens and webhook URLs secret, and review which alerts or reports may be sent externally.