ClawHub

Placed

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Placed career-platform skill, but users should be aware it stores a Placed API key locally and sends career content to Placed’s API.

Install only if you are comfortable sharing relevant career data with Placed. Use a dedicated, revocable API key, protect or delete ~/.config/placed/credentials when no longer needed, and review important resume, cover letter, or job-tracker changes before the agent sends them.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Context-Inappropriate Capability

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs reading credentials from the user's home directory and persisting an API key to disk, which expands its access to local secrets beyond the core stated function of career assistance. This creates unnecessary secret-handling risk: a compromised or overly broad skill workflow could access, overwrite, or leave sensitive credentials stored in plaintext without user awareness or consent.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The trigger description is very broad and covers many common job-search activities, increasing the chance the skill is invoked in situations where users did not intend to send career data to a third-party service. In this context, broad activation matters because the skill can collect resumes, job applications, and other sensitive professional information and transmit it externally.

Missing User Warnings

High
Confidence
98% confidence
Finding
The skill directs the user or agent to save the API key in plaintext under ~/.config/placed/credentials without any warning about local credential persistence, file permissions, or shared-machine risk. Plaintext storage of bearer tokens can enable account compromise if the workstation, backups, shell tooling, or other local processes can read that file.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal