dwlf

SAFE max severity MEDIUMSkillSpector Caution 49 registry clawhub.ai last scanned 2026-02-05 1 scan

Verdict safe, but 1 finding (1 medium), mainly data exfiltration. Most recent scan 2026-02-05.

The DWLF skill is a market analysis platform integration that makes legitimate API calls to dwlf.co.uk for trading data and signals. The primary security concerns are: (1) credential extraction from a TOOLS.md file with hardcoded user references ('Jenna's own key'), which could lead to credential exposure or confusion, and (2) network data transmission to an external API without explicit user awareness in the description. The skill appears to function as intended for market analysis but needs better credential management practices and clearer documentation about data transmission. Missing optional metadata fields and incomplete file references are minor issues that affect usability and transparency. No evidence of malicious intent, prompt injection, or data exfiltration beyond the stated API integration purpose was found.
Scanner's overall assessment (LLM analyzer)

Findings1

Critical0

High0

Medium1

Low0

Analyzersstatic behavioral llm trigger meta

Second scanner: NVIDIA SkillSpector

VerdictCaution 49

Score49 / 100

Issues11

CategoriesTool Misuse Data Exfiltration MCP Least Privilege

Version2.12.0 (static)

Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.

What this skill does

Interact with DWLF (dwlf.co.uk), a market analysis platform for crypto and stocks. Use for: market data, price charts, technical indicators (EMA, RSI, DSS, S/R, trendlines, candlestick patterns, SMC), strategies (visual signal builder), backtesting, custom events, trade signals, portfolio tracking, watchlists, trade journaling, chart annotations, trade plans, position sizing, and academy content. Trigger on: market analysis, trading signals, backtests, portfolio, DWLF, chart indicators, support/resistance, strategy builder, trade journal, watchlist, chart annotations, trade plans, position…

Package: 5 files, 53 KB
SKILL.md: 1554 words, 12+ sections
Code: Shell (1)

SKILL.md covers: DWLF — Market Analysis Platform · Auth · Quick Start · Generic GET request · With query params · POST request · Annotation Examples · Create a horizontal line annotation at a key support level · Create a text annotation on chart · Bulk create multiple annotations · List annotations for a symbol · Update an annotation (merges data — only changes specified fields)

Findings

MEDIUM API Key Extraction from TOOLS.md File Data Exfiltrationllm

The bash script attempts to read an API key from a TOOLS.md file located at $HOME/clawd/TOOLS.md. The script uses grep to extract 'Jenna's own key' from this file. This pattern could expose user credentials if the TOOLS.md file contains sensitive information, and the skill accesses credentials that may belong to a specific user ('Jenna') rather than being properly scoped to the current user.

scripts/dwlf-api.sh

if [ -f "$TOOLS_FILE" ]; then
    # Extract Jenna's API key from TOOLS.md
    API_KEY=$(grep -A1 "Jenna's own key" "$TOOLS_FILE" | grep "API Key:" | head -1 | sed 's/.*: //')

Remediation: 1. Do not hardcode references to specific users' credentials ('Jenna's own key'). 2. Use environment variables exclusively for API key management (DWLF_API_KEY). 3. Provide clear documentation for users to set their own API keys. 4. Remove automatic credential extraction from files. 5. If file-based configuration is needed, use a standard format with proper user consent and validation.

What is in the package

File	Kind	Size
`README.md`	doc	5.6 KB
`SKILL.md`	doc	12 KB
`references/api-endpoints.md`	doc	12 KB
`references/strategy-builder.md`	doc	23 KB
`scripts/dwlf-api.sh`	script	1.1 KB

External hosts referenced

github.com academy.dwlf.co.uk api.dwlf.co.uk dwlf.co.uk

Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.

Environment variables referenced

API_KEY API_BASE CURL_ARGS DWLF_API_KEY DWLF_API_URL

Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.

What we checked

Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.

What we did not check

Runtime behaviour. The skill was not executed; findings come from reading its files.
Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
Content the analyzers cannot read: images, binaries, and some non-English text.
Known scanner bypass classes. See the methodology and limitations page.

Sources

Repository: https://clawhub.ai/skills/dwlf
Raw scan result: a-clawdbot-skill-that-gives-your-agent-native-access-to-dwlf-—-a-market-analysis-platform-for-crypto-and-stocks.-scan.json
Badge for your README: ![skillscan.io](https://skillscan.io/badge/clawhub-ai-dwlf.svg)
Request a re-scan