Scan Report
5 /100
finresearchclaw
Finance, accounting, and investment research automation via the FinResearchClaw repo
Legitimate finance research automation skill that safely clones a public GitHub repo and runs documented research workflows with no hidden functionality.
Safe to install
No action needed. The skill is safe for use.
Findings 1 items
| Severity | Finding | Location |
|---|---|---|
| Low | allowedTools not explicitly declared in SKILL.md Doc Mismatch | SKILL.md:1 |
| Resource | Declared | Inferred | Status | Evidence |
|---|---|---|---|---|
| Filesystem | NONE | WRITE | ✓ Aligned | SKILL.md references writing to ~/.openclaw/workspace/ |
| Network | NONE | READ | ✓ Aligned | install_or_update.sh clones from github.com |
| Shell | NONE | WRITE | ✓ Aligned | run_finance_example.sh executes pip install and researchclaw |
File Tree
6 files · 5.5 KB · 178 lines Markdown 2f · 112L
Shell 3f · 61L
JSON 1f · 5L
├─
▾
references
│ └─
examples.md
Markdown
├─
▾
scripts
│ ├─
choose_runner.sh
Shell
│ ├─
install_or_update.sh
Shell
│ └─
run_finance_example.sh
Shell
├─
_meta.json
JSON
└─
SKILL.md
Markdown
Security Positives
✓ All shell operations are fully documented in SKILL.md helper scripts section
✓ No credential access attempted (no ~/.ssh, ~/.aws, .env reads)
✓ No base64, obfuscation, or eval patterns found
✓ No external IP connections beyond github.com
✓ No data exfiltration or C2 indicators
✓ Repo operations limited to a single well-known GitHub source
✓ pip install uses editable mode (-e) from a pinned local path only
✓ No cron, persistence, or backdoor mechanisms
✓ Scripts use set -euo pipefail for safe execution
✓ No high-risk indicators (reverse shell, credential harvesting, curl|bash)