Elasticsearch

PendingStatic analysis audit pending.

Overview

No static analysis result has been recorded yet. Pattern checks will appear here once the artifact has been analyzed.

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.

Note

ASI02: Tool Misuse and Exploitation

What this means

An agent following these examples with a sufficiently privileged API key could delete or alter Elasticsearch data or configuration.

Why it was flagged

The skill documents destructive Elasticsearch operations, including wildcard deletion. This is relevant to the skill's administration purpose, but it can cause significant data loss if used without explicit user direction.

Skill content

## Delete Index

```bash
es "my-old-index" -XDELETE
```

**With wildcard** (dangerous — requires `action.destructive_requires_name: false`):
```bash
es "temp-*" -XDELETE
```

Recommendation

Use least-privilege API keys, prefer read-only keys for search tasks, and require explicit user confirmation with exact index/object names before DELETE, update-by-query, delete-by-query, reindex, cluster-setting, or overwrite operations.

Note

ASI03: Identity and Privilege Abuse

What this means

A broad API key could allow the agent to read sensitive logs, write documents, change settings, or delete data in the connected cluster.

Why it was flagged

The skill requires a user-provided Elasticsearch API key and uses it in Authorization headers. This is expected for the integration, but the key's privileges determine how much data the agent can read or change.

Skill content

Every request needs the cluster URL and an API key:

ES_URL="https://your-cluster.es.cloud.elastic.co:443"
ES_API_KEY="your-base64-api-key"
...
If the user provides a URL and key, export them as `ES_URL` and `ES_API_KEY` before running commands.

Recommendation

Create a narrowly scoped API key for the specific task, avoid sharing production admin keys, and rotate the key if it is exposed in chat, shell history, logs, or saved files.

Note

ASI04: Agentic Supply Chain Vulnerabilities

What this means

Users installing from a different repository state than the reviewed artifact could receive changed instructions.

Why it was flagged

The README instructs users to manually clone and copy skill files from an external GitHub repository, while the registry metadata lists the source as unknown. The provided artifact is instruction-only, so this is a provenance note rather than an executable-code concern.

Skill content

git clone https://github.com/davidgeorgehope/elasticsearch-skill.git
mkdir -p ~/.claude/skills/elasticsearch
cp elasticsearch-skill/SKILL.md ~/.claude/skills/elasticsearch/
cp -r elasticsearch-skill/references ~/.claude/skills/elasticsearch/

Recommendation

Install from a trusted, reviewed revision and compare the local files with the reviewed package before using it with sensitive Elasticsearch credentials.