Skills/ClawHub/gmailcleanerv2

gmailcleanerv2@1.0.0

CAUTION· static only

Publisher claims: "Read/search Gmail via gog CLI (preferred) or Python scripts (fallback). Inbox check, email search, content retrieval, IMAP support." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher coorops25 · publishing for 265 daysInstalls 1,269Last detonated 56 min ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-18 and scored it 56/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompt injection attempt; Access to sensitive file paths. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

CRITICAL
Prompt injection attemptmnt/user-data/outputs/email-manager-v3/email-analyzer/SKILL.md:64 · Prompt injection attempt — 'ignore previous instructions'Patrones: "Ignore previous instructions", "You are now", "Act as", "Forget your training"Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathsmnt/user-data/outputs/email-manager-v3/email-analyzer/SKILL.md:95 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- `ANTHROPIC_API_KEY` unset → configurar en entorno o `.env`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionanalyzer.py:6 · File type combined with upload action — agent may exfiltrate local data filespython3 analyzer.py --emails-file emails.json --output analysis.jsonFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionmnt/user-data/outputs/email-manager-v3/email-analyzer/SKILL.md:49 · File type combined with upload action — agent may exfiltrate local data filespython3 scripts/analyzer.py --emails-file emails.json --output analysis.jsonFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedscheduler.py:32 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionmnt/user-data/outputs/email-manager-v3/email-reporter/SKILL.md:63 · File type combined with upload action — agent may exfiltrate local data filesgog docs export <DOC_ID> --format txt --out /tmp/informe.txt --no-inputFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈5,312 tok
6 files · 22 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

24 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim coorops25: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim coorops25Propose a patch to the maintainer