Caveat verdict
Claude Dev Setup
claude-dev-setup
Writes files AND executes processes
Extracts the user's own Claude Code OAuth token from `~/.claude/.credentials.json` for local automation use; the token is the agent's own credential used locally and is not sent anywhere external.
Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
What it does
These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Writes files AND executes processes — may drop and execute malicious scripts
LLM05 · LLM06 · ASI05
Installs packages AND executes processes — opaque dependency chain with execution
LLM03 · ASI04
Accesses credentials AND writes files — may persist stolen credentials locally
LLM02 · LLM06 · ASI03
Accesses agent memory AND writes files — may modify agent behavior persistently
LLM01 · LLM06 · ASI01 · ASI06
Permission integrity
credential_access
package_install
agent_memory
Findings (4)
Possible hardcoded credential
SKILL.md · code · TOKEN="sk-ant-oat01-xxxxx...
Accesses shell history/config
SKILL.md · code · ~/.zshrc
Uses exec() — may execute shell commands
SKILL.md · code · exec(
References agent configuration files
SKILL.md · code · CLAUDE.md
Permissions & capabilities
Requires 1 system binary.
agent_memorycredential_accessprocess_execfile_writepackage_install Thanks — recorded.