developer-experience
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a shell command (
ls) on specific local directories (e.g.,~/.claude/skills/,~/.agent/skills/) to identify which companion skills are currently installed. This is used solely for the 'Companion check' feature to provide installation recommendations for missing dependencies, which is a legitimate and transparent functional behavior. - [PROMPT_INJECTION]: The skill contains a directive to start responses with a specific emoji (🧢) when activated. This is a benign stylistic instruction and does not attempt to bypass safety filters or override core agent behavior.
- [REMOTE_CODE_EXECUTION]: The documentation includes examples of using
npxcommands (e.g.,npx @acme/migrate) andnpm installfor the user to follow. These are illustrative examples for SDK consumers and do not involve the skill itself executing remote code or scripts at runtime.
Audit Metadata