CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gog

Use the gog CLI when Google connectors lack an operation, shell automation needs stable JSON, or local Google auth needs inspection. Shared account, auth, output, and safety guidance for all gog service skills.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security
Critical

E004: Prompt injection detected in skill instructions.

What this means

Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.

Why it was flagged

The skill is a legitimate gog CLI guide, but it has medium-risk content: it steers agents toward broad OAuth scopes instead of least privilege, shows a silent BCC to a third party in a reply recipe, and tells the agent to click the low-emphasis control past Google's unverified-app warning.

Report incorrect finding
Medium

W013: Attempt to modify system services in skill instructions.

What this means

The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.

Why it was flagged

The skill is mainly a Google CLI usage guide, but it tells the agent to fix the service or systemd/OpenClaw environment and to set keyring variables in launching processes, which edges toward modifying service configuration, and it has the agent drive OAuth reauth and port forwarding.

Low

W011: Third-party content exposure detected (indirect prompt injection risk).

What this means

The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.

Why it was flagged

The required read workflows run `gog gmail search`, `gmail get`, and `gmail thread get` (and calendar events) over the user's inbox, which outsiders can email into without the agent selecting a specific item first, so this is medium exposure despite the `--wrap-untrusted` and `--sanitize-content` mitigations.

Repository

openclaw/gogcli

Path

.agents/skills/gog/SKILL.md

Audited
Security analysis
Snyk

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.