Security audit
Security checks across malware telemetry and agentic risk
This skill does what it says: compresses user-selected natural-language memory files with Claude, backs up the original, and avoids obvious code or secret files.
Install only if you are comfortable sending the selected memory file to Claude/Anthropic for processing. Do not run it on files containing secrets or private notes you would not upload to a third-party model, and use the explicit /caveman:compress <filepath> form so the target file is clear.
def call_claude(prompt: str) -> str:
api_key = os.environ.get("ANTHROPIC_API_KEY")
if api_key:
try:
import anthropicpass # anthropic not installed, fall back to CLI
# Fallback: use claude CLI (handles desktop auth)
try:
result = subprocess.run(
["claude", "--print"],
input=prompt,
text=True,# Filenames and paths that almost certainly hold secrets or PII. Compressing
# them ships raw bytes to the Anthropic API — a third-party data boundary that
# developers on sensitive codebases cannot cross. detect.py already skips .env
# by extension, but credentials.md / secrets.txt / ~/.aws/credentials would
# slip through the natural-language filter. This is a hard refuse before read.
SENSITIVE_BASENAME_REGEX = re.compile(
r"(?ix)^("SENSITIVE_BASENAME_REGEX = re.compile(
r"(?ix)^("
r"\.env(\..+)?"
r"|\.netrc"
r"|credentials(\..+)?"
r"|secrets?(\..+)?"
r"|passwords?(\..+)?"# Filenames and paths that almost certainly hold secrets or PII. Compressing
# them ships raw bytes to the Anthropic API — a third-party data boundary that
# developers on sensitive codebases cannot cross. detect.py already skips .env
# by extension, but credentials.md / secrets.txt / ~/.aws/credentials would
# slip through the natural-language filter. This is a hard refuse before read.
SENSITIVE_BASENAME_REGEX = re.compile(
r"(?ix)^("# Filenames and paths that almost certainly hold secrets or PII. Compressing # them ships raw bytes to the Anthropic API — a third-party data boundary that # developers on sensitive codebases cannot cross. detect.py already skips .env # by extension, but credentials.md / secrets.txt / ~/.aws/credentials would # slip through the natural-language filter. This is a hard refuse before read. SENSITIVE_BASENAME_REGEX = re.compile(
# Extensions that are code/config and should be skipped
SKIP_EXTENSIONS = {
".py", ".js", ".ts", ".tsx", ".jsx", ".json", ".yaml", ".yml",
".toml", ".env", ".lock", ".css", ".scss", ".html", ".xml",
".sql", ".sh", ".bash", ".zsh", ".go", ".rs", ".java", ".c",
".cpp", ".h", ".hpp", ".rb", ".php", ".swift", ".kt", ".lua",
".dockerfile", ".makefile", ".csv", ".ini", ".cfg",if ext in COMPRESSIBLE_EXTENSIONS:
return "natural_language"
if ext in SKIP_EXTENSIONS:
return "code" if ext not in {".json", ".yaml", ".yml", ".toml", ".ini", ".cfg", ".env"} else "config"
# Extensionless files (like CLAUDE.md, TODO) — check content
if not ext:62/62 vendors flagged this skill as clean.
No suspicious patterns detected.