caveman-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"
65
77%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./plugins/caveman/skills/caveman-compress/SKILL.mdThe canonical home for this skill is caveman-compress in JuliusBrussee/caveman
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill instructs the model to preserve code blocks, inline code, URLs, commands and environment variables "EXACTLY" and to call an external model to compress files, which forces the LLM to include any secrets that might appear verbatim in those regions (e.g., API keys, tokens, passwords) in its outputs or when sending data to the compressor.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The skill’s required runtime workflow (CLI → `compress_file` → `call_claude`) reads the user-specified local `<filepath>` contents—i.e., outsider-authored free text written into that file—and sends the file body to Claude for compression/fix.
- Repository
- JuliusBrussee/caveman
- Commit
14d4f2e
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.