Qlik Cloud

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

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.

ConcernHigh Confidence
ASI05: Unexpected Code Execution
What this means

A maliciously crafted question or other untrusted argument could potentially run commands with the same local privileges as the agent.

Why it was flagged

The user-supplied question is inserted directly into Python source code passed to python3 -c. A crafted question containing triple quotes and Python statements could break out of the string and execute local code.

Skill content
QUESTION="${2:-}" ... echo "$RESPONSE" | python3 -c " ... question = '''$QUESTION'''
Recommendation

Do not interpolate shell variables into Python source. Pass values through argv, environment variables, stdin, or JSON, and validate IDs before use.

What this means

The agent may be able to change or delete Qlik tenant resources when given a sufficiently privileged API key.

Why it was flagged

The skill exposes documented mutating operations, including deleting Qlik apps; this is purpose-aligned but high impact if the wrong ID is used or the agent acts without confirmation.

Skill content
| `qlik-app-delete.sh` | Delete app | `<app-id>` |
Recommendation

Use explicit human confirmation for delete, run, cancel, trigger, and reload actions; verify resource IDs; prefer read-only or least-privilege credentials for analysis-only use.

What this means

If the API key is broad, the agent can access business data, users, licenses, apps, automations, alerts, and other tenant resources.

Why it was flagged

The skill requires a Qlik API key, which grants whatever tenant permissions that key has. This is expected for the integration, but it is sensitive account authority.

Skill content
Add credentials to TOOLS.md: ... Tenant URL: https://your-tenant.region.qlikcloud.com ... API Key: your-api-key-here
Recommendation

Store the key securely, keep TOOLS.md private, use the narrowest Qlik permissions practical, and revoke the key when no longer needed.

What this means

Questions and related assistant responses may be stored or processed in the Qlik tenant's AI assistant service.

Why it was flagged

The script sends user questions to a Qlik Answers AI assistant and may create a remote conversation thread. This is purpose-aligned but affects where prompts and answers are stored.

Skill content
# If no thread-id provided, creates a new thread automatically. ... /api/v1/assistants/${ASSISTANT_ID}/threads/${THREAD_ID}/actions/invoke
Recommendation

Avoid sending sensitive prompts unless Qlik tenant policy permits it, and manage thread retention according to organizational requirements.

What this means

Installation or execution may fail on systems without these tools, and users may not see the dependency requirements in registry metadata.

Why it was flagged

The README lists local runtime dependencies, while the registry requirements say no required binaries. This is an install-contract gap rather than evidence of malicious behavior.

Skill content
Requirements: - bash - curl - Python 3 (standard library only)
Recommendation

Declare bash, curl, Python 3, QLIK_TENANT, and QLIK_API_KEY in the skill metadata so users can review requirements before installation.