caveman-compress
What this skill does
Compress natural language memory files (e.g., CLAUDE.md, todos, preferences) into a more compact format to save input tokens. Preserves technical substance, code, URLs, and structure.
github/juliusbrussee - Data Exfiltration - 97.3k stars
Threat analysis
Skill info
pkg:github/JuliusBrussee/caveman@3098342?skill=caveman-compressAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/compress.py
The script calls `subprocess.run([claude_bin, "--print"], input=prompt, ...)` which suggests it is sending the contents of files to an external service (Claude) for compression. This is a data boundarInsecure File Handling
Insecure File Handling via local-llm-review
scripts/compress.py
The script does not appear to sanitize or validate the input file before processing it, which could lead to unintended file processing or data leakage.Badge
Add the Anomity scan badge for caveman-compress to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of caveman-compress? Report an issue or request a rescan.
