caveman-setup
Verdict safe, but 1 finding (1 info), mainly policy violation. Most recent scan 2026-10-22.
Second scanner: NVIDIA SkillSpector
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
Wire a repository through the Caveman Cloud gateway so every LLM request is measured, with no behavior change. Use for "set up caveman" or adding LLM spend observability.
- Package
- 1 file, 10 KB
- SKILL.md
- 1393 words, 10 sections
- Code
- None. Instructions only.
SKILL.md covers: Rules (non-negotiable) · Step 1 — Find every live LLM callsite · Step 2 — Pick the app slug · Step 3 — Wire each callsite · Step 4 — Verify with one real request · OpenAI-protocol wiring: · Anthropic-protocol wiring: · Step 5 — Report · Caveman is live in this repo · Failure templates (use verbatim, filled in — never soften)
Findings
INFO Skill does not specify a license Policy Violationstatic
Skill manifest does not include a 'license' field. Specifying a license helps users understand usage terms.
SKILL.md
What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 10 KB |
External hosts referenced
gateway.caveman.so app.caveman.so
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
CAVE_API_KEY CAVE_GATEWAY_URL OPENAI_API_KEY ANTHROPIC_BASE_URL GEMINI_BASE_URL GOOGLE_GEMINI_BASE_URL OPENAI_API_BASE OPENAI_BASE_URL PROVIDER_KEY PROVIDER_KEYS
Package contents recorded 2026-10-22 at commit bad48a0e1df5. 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.
- Bytecode analyzer.
- Pipeline analyzer.
- Correlation analyzer.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
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://github.com/juliusbrussee/caveman
- Raw scan result: juliusbrussee-caveman-skills-caveman-setup-scan.json
- Badge for your README:
- Request a re-scan