ez-google
2 findings (1 high, 1 medium), mainly data exfiltration. Most recent scan 2026-02-01.
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Google Workspace tools for Gmail, Calendar, Drive, Docs, Sheets, Slides, Contacts, and Chat.
- Package
- 10 files, 44 KB
- SKILL.md
- 388 words, 10 sections
- Code
- Python (9)
SKILL.md covers: ez-google · Auth (do this first) · Gmail · Calendar · Drive · Docs · Sheets · Slides · People/Contacts · Chat (Workspace only)
Findings
HIGH Suspicious URL detected: https://ezagentauth.com Data Exfiltrationbehavioral
Script contains suspicious URL that may be used for data exfiltration
skills/clawhub-ez-google/scripts/auth.py
MEDIUM Reading environment variables that may contain secrets Data Exfiltrationstatic
Pattern detected: os.environ.get("GOOGLE_CLIENT_SECRET
scripts/auth.py:62
client_secret = os.environ.get("GOOGLE_CLIENT_SECRET")What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 3.0 KB |
scripts/auth.py | script | 7.3 KB |
scripts/chat.py | script | 3.9 KB |
scripts/docs.py | script | 4.4 KB |
scripts/drive.py | script | 4.1 KB |
scripts/gcal.py | script | 4.4 KB |
scripts/gmail.py | script | 4.4 KB |
scripts/people.py | script | 4.1 KB |
scripts/sheets.py | script | 4.2 KB |
scripts/slides.py | script | 3.6 KB |
External hosts referenced
www.googleapis.com accounts.google.com docs.google.com ezagentauth.com oauth2.googleapis.com
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
GOOGLE_CLIENT_ID GOOGLE_CLIENT_SECRET
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/ez-google
- Raw scan result: ez-google-scan.json
- Badge for your README:
- Request a re-scan