Personio Recruiting

Security checks across malware telemetry and agentic risk

Overview

The skill is aligned with Personio Recruiting, but it gives broad authenticated access to run direct Personio API requests, including write/delete methods, without clear guardrails.

Install only if you trust Membrane and are comfortable connecting it to Personio Recruiting. Treat read-only queries differently from changes: require explicit approval for any create, update, patch, or delete request, and review the exact API endpoint and payload before allowing the agent to run it.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI02: Tool Misuse and Exploitation
Medium
What this means

An agent could make broad changes to Personio Recruiting records if a user authorizes the connection and asks for—or the agent infers—an action involving data changes.

Why it was flagged

The skill documents a broad authenticated API escape hatch, including write and delete methods, without visible limits or confirmation requirements for high-impact recruiting-data changes.

Skill content
“you can send requests directly to the Personio Recruiting API through Membrane's proxy” ... “HTTP method (GET, POST, PUT, PATCH, DELETE)”
Recommendation

Require explicit user approval before POST, PUT, PATCH, or DELETE requests; prefer narrowly scoped discovered actions; review the exact endpoint, payload, and expected effect before running proxy commands.

#
ASI03: Identity and Privilege Abuse
Medium
What this means

The connected account may allow reading or changing recruiting data such as candidates, job offers, requisitions, schedules, or templates.

Why it was flagged

The integration requires delegated Membrane/Personio authentication and ongoing credential refresh, which is expected for this service but sensitive.

Skill content
“Membrane handles authentication and credentials refresh automatically” and “membrane login --tenant --clientName=<agentType>”
Recommendation

Use the least-privileged Personio/Membrane account available, confirm the connection scope, and revoke the connection when it is no longer needed.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

Installing the latest global CLI means future package changes could affect what runs locally.

Why it was flagged

The skill relies on installing/running the latest Membrane CLI from npm rather than a pinned version. This is central to the stated integration but leaves behavior dependent on the current package.

Skill content
“npm install -g @membranehq/cli@latest” and “npx @membranehq/cli@latest action list”
Recommendation

Install only from a trusted npm registry, verify the package publisher, and consider pinning or reviewing the CLI version in controlled environments.

#
ASI07: Insecure Inter-Agent Communication
Medium
What this means

Candidate and hiring data may pass through Membrane infrastructure as part of normal use.

Why it was flagged

Personio API traffic and authentication handling are routed through Membrane as a gateway. This is disclosed and purpose-aligned, but it affects sensitive recruiting data boundaries.

Skill content
“send requests directly to the Personio Recruiting API through Membrane's proxy” and “injects the correct authentication headers”
Recommendation

Confirm Membrane’s privacy, retention, and compliance posture before using this with sensitive applicant or HR data.