Qlik Cloud
v1.0.3Complete Qlik Cloud analytics platform integration with 37 tools. Health checks, search, app management, reloads, natural language queries (Insight Advisor), automations, AutoML, Qlik Answers AI, data alerts, spaces, users, licenses, data files, and lineage. Use when user asks about Qlik, Qlik Cloud, Qlik Sense apps, analytics dashboards, data reloads, or wants to query business data using natural language.
⭐ 1· 2.1k·0 current·0 all-time
by@undsoul
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The scripts and documentation implement a full Qlik Cloud integration (health, apps, reloads, Insight Advisor, automations, AutoML, Answers, alerts, lineage). That functionality is coherent with the skill name/description. However, the registry metadata lists no required environment variables or primary credential even though every script and the SKILL.md require QLIK_TENANT and QLIK_API_KEY. This metadata omission is an important mismatch.
Instruction Scope
SKILL.md and the included scripts limit runtime actions to calling the Qlik Cloud tenant API (constructed from QLIK_TENANT) with the QLIK_API_KEY. Scripts do not attempt to read arbitrary host files or send data to non-tenant endpoints. They do create a temporary file (/tmp/qlik_delete_response.txt) only when handling delete responses. Instructions do ask the user to add credentials to TOOLS.md and to run scripts with QLIK_TENANT/QLIK_API_KEY environment variables.
Install Mechanism
There is no install spec (instruction-only installer behavior). Files are provided as scripts (bash + python3). No external downloads, package installs, or extract-from-URL steps are present in the manifest, which lowers install-time risk.
Credentials
The runtime requires two environment values (QLIK_TENANT and QLIK_API_KEY) which are appropriate and minimal for the stated purpose. However, the registry metadata declares no required env vars and no primary credential. That inconsistency is problematic: the skill should have declared QLIK_API_KEY as the primary credential and listed the required env variables. The requested environment access (tenant URL + API key) is otherwise proportionate to the functionality.
Persistence & Privilege
The skill does not request always:true and does not appear to modify other skills or system-wide settings. It will be user-invocable and can be invoked autonomously by the agent (platform default), which is normal for skills.
What to consider before installing
Before installing, note these issues and take steps to mitigate risk:
- The skill's scripts and SKILL.md require QLIK_TENANT and QLIK_API_KEY, but the skill registry metadata did not declare those env vars or a primary credential. Ask the publisher to update the metadata (primaryEnv should be QLIK_API_KEY and requires.env should include QLIK_TENANT and QLIK_API_KEY).
- Review the included scripts yourself (they are plain bash + small python3 JSON parsers). They call only the Qlik tenant URL you supply; they do not call other external endpoints. Still, verify the tenant URL you provide is correct and trusted.
- Use least-privilege API keys: create an API key with the minimum privileges needed (read-only where possible) and test in a non-production tenant or with a low-privilege account first. Revoke the key if you later stop using the skill.
- Because some scripts trigger actions (delete app, run automations, trigger alerts, run reloads), restrict who can invoke the skill and confirm operator intent before running destructive actions.
- The delete script writes a temporary file to /tmp; ensure your environment's /tmp is monitored if that's a policy concern.
- If you require higher assurance, ask the publisher for an updated package that correctly declares required env vars and a primary credential, and for a short explanation of why each API action is needed.
Confidence note: The behavior appears to match the advertised purpose and no obvious exfiltration patterns are present, but the metadata omissions and the fact this package contains executable scripts rather than being purely declarative make this suspicious rather than outright benign.Like a lobster shell, security has layers — review code before you run it.
latestvk973ejmnsmqastrba22d2ks7dx80gzcj
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
