engineering-skills

No clear supply-chain malware indicators are present (no obfuscation, no dynamic execution, no suspicious external network exfiltration logic). The primary security concern is credential disclosure: bulk provisioning exports plaintext per-user passwords to a CSV file, creating an at-rest secret exposure risk. Secondary concerns are high-impact privileged operations (Conditional Access policy creation and user/mailbox lifecycle changes) that require strict access control, auditing, and careful use of WhatIf/report-only modes.

This module is primarily a command orchestration catalog for Google Workspace-related CLI operations. It shows no overt malware indicators (no credential theft, exfiltration, persistence, or obfuscation) in the provided fragment. However, it contains a high-impact structural risk: it executes shell command strings via subprocess.run(..., shell=True) sourced from a recipe catalog. If the catalog or missing surrounding code performs placeholder interpolation or can be tampered with, the tool could become an arbitrary command execution vector. Treat as security-sensitive, especially in a supply-chain threat model.

SUSPICIOUS. The operational scope fits a Google Workspace admin skill, and data flows appear directed to Google APIs, but the install instructions are not internally consistent with the claimed project: the skill mixes an Anthropic npm package with a Google Workspace GitHub repo and an incorrect Cargo package name. That is a trust and provenance issue rather than confirmed malware.

No strong evidence of covert malware (e.g., exfiltration, backdoor/persistence, or obfuscated payloads) is present in the provided fragment. However, the module generates highly privileged Microsoft 365 administration scripts and directly interpolates user-controlled fields into PowerShell code without visible escaping, creating a realistic script/command injection risk if attacker-controlled inputs can reach script generation/execution. It also embeds a weak default initial password pattern, which is an operational security concern. The snippet appears malformed/incomplete, so certainty is limited, but overall security risk remains moderate-to-high due to privileged automation and insecure templating.

SUSPICIOUS. The top-level skill is mostly a catalog/loader and is broadly consistent with its stated purpose, but it relies on a third-party npm installer and creates a transitive trust chain into many downstream skills, including potentially high-risk security and cloud capabilities. No direct credential harvesting, exfiltration, or malicious execution is visible in this specific SKILL text.