caveman-compress

ISSUES FOUND max severity HIGHSkillSpector Do not install 100 registry juliusbrussee last scanned 2026-10-22 2 scans

7 findings (2 high, 4 medium, 1 info), mainly data exfiltration, social engineering, unauthorized tool use. Most recent scan 2026-10-22.

Findings7

Critical0

High2

Medium4

Low0

Analyzersstatic bytecode pipeline correlation behavioral trigger

Scanner version2.3.1

Second scanner: NVIDIA SkillSpector

VerdictDo not install 100

Score100 / 100

Issues13

CategoriesPrivilege Escalation Data Flow Data Exfiltration

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

Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Sends the file's text to the configured model provider. Trigger: /caveman-compress.

Package: 10 files, 89 KB
SKILL.md: 803 words, 11 sections
Code: Python (7)

SKILL.md covers: Caveman Compress · Purpose · Trigger · Process · Compression Rules · Remove · Preserve EXACTLY (never modify) · Preserve Structure · Compress · Pattern · Boundaries

Findings

HIGH Credential file access detected Data Exfiltrationbehavioral

Script accesses credential files in /Users/brianlevine/claude-projects/skill-scanner-test/skills/juliusbrussee-caveman/skills/caveman-compress/scripts/compress.py

/Users/brianlevine/claude-projects/skill-scanner-test/skills/juliusbrussee-caveman/skills/caveman-compress/scripts/compress.py

Remediation: Remove access to ~/.aws, ~/.ssh, or other credential files

HIGH Sensitive source reaches a network sink Data Exfiltrationcorrelation

Correlated sensitive_environment → network behavior across scripts/compress.py.

scripts/compress.py:690

Remediation: Remove the transmission or constrain it to explicitly declared, trusted destinations.

MEDIUM Potential description-behavior mismatch Social Engineeringstatic

Skill performs actions not reflected in its description

SKILL.md

Remediation: Ensure description accurately reflects all skill capabilities

MEDIUM Undeclared network usage Unauthorized Tool Usestatic

Skill code uses network libraries but doesn't declare network requirement

SKILL.md

Remediation: Declare network usage in compatibility field or remove network calls

MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic

Pattern detected: urllib.request.Request(

scripts/compress.py:679

request = urllib.request.Request(

Remediation: Ensure network operations are necessary and document allowed destinations

MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic

Pattern detected: urllib.request.urlopen(

scripts/compress.py:690

with urllib.request.urlopen(request, timeout=CLAUDE_CALL_TIMEOUT_SECONDS) as response:

Remediation: Ensure network operations are necessary and document allowed destinations

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

Remediation: Add 'license' field to SKILL.md frontmatter (e.g., MIT, Apache-2.0)

What is in the package

File	Kind	Size
`README.md`	doc	7.6 KB
`SECURITY.md`	doc	4.1 KB
`SKILL.md`	doc	5.4 KB
`scripts/__init__.py`	script	224 B
`scripts/__main__.py`	script	30 B
`scripts/benchmark.py`	script	2.4 KB
`scripts/cli.py`	script	2.4 KB
`scripts/compress.py`	script	46 KB
`scripts/detect.py`	script	5.0 KB
`scripts/validate.py`	script	16 KB

External hosts referenced

em-content.zobj.net github.com

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

XDG_DATA_HOME ANTHROPIC_API_KEY CAVEMAN_COMPRESS_MODEL CAVEMAN_MODEL OPENCODE_CONFIG_CONTENT CAVEMAN_COMPRESS_API_KEY CAVEMAN_COMPRESS_ENDPOINT CAVEMAN_MAX_OUTPUT_TOKENS

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.

Scan history

Date	Verdict	Findings	Change	Analyzers	Raw
2026-10-22	HIGH	7	=	static bytecode pipeline correlation behavioral trigger	JSON
2026-10-22	HIGH	7	first scan	static bytecode pipeline correlation behavioral trigger	JSON

Sources

Repository: https://github.com/juliusbrussee/caveman
Raw scan result: juliusbrussee-caveman-skills-caveman-compress-scan.json
Badge for your README: ![skillscan.io](https://skillscan.io/badge/juliusbrussee-caveman-compress.svg)
Request a re-scan

Second scanner: NVIDIA SkillSpector

What this skill does

Findings

What is in the package

External hosts referenced

Environment variables referenced

What we checked

What we did not check

Scan history

Sources

Related skills