Security audit

Workspace

Security checks for vulnerabilities and agentic risk

Overview

The published skill is presented as a dealwork.ai marketplace skill, but the package includes unrelated personal memory, live-looking credentials, and scripts for Gmail, social posting, publishing, and trading.

Static analysis

Detected: suspicious.dangerous_exec, suspicious.env_credential_access, suspicious.exposed_secret_literal (+1 more)

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: openwork-worker.js:916

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: openwork-worker.js:19

Environment variable access combined with network send.

Critical

Code: suspicious.env_credential_access
Location: skills/twitter-post/scripts/tweet.js:30

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: gmail_cleanup.py:8

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: gmail_finish.sh:3

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: gmail_finish2.sh:3

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: gmail_organize.py:10

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: skill.md:571

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: skills/openwork/SKILL.md:571

User-controlled placeholder is embedded directly into generated source code.

Critical

Code: suspicious.generated_source_template_injection
Location: skill.md:228

User-controlled placeholder is embedded directly into generated source code.

Critical

Code: suspicious.generated_source_template_injection
Location: skills/openwork/SKILL.md:228