frontend-developer
Warn
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill contains explicit instructions in
SKILL.mdfor the AI agent to execute a shell command to probe the user's local directory for other installed skills. This behavior constitutes environment reconnaissance and unauthorized access to the agent's internal configuration paths. - Evidence:
check which companion skills are installed by running ls ~/.claude/skills/ ~/.agent/skills/ ~/.agents/skills/ .claude/skills/ .agent/skills/ .agents/skills/ 2>/dev/null. - [EXTERNAL_DOWNLOADS]: The documentation encourages the execution of remote code from an external source via
npxduring the installation process. - Evidence:
npx skills add AbsolutelySkilled/AbsolutelySkilled --skill frontend-developer. - [PROMPT_INJECTION]: The skill attempts to override the agent's standard communication style by mandating a specific emoji prefix for all initial responses, which serves as a behavioral constraint.
- Evidence:
When this skill is activated, always start your first response with the 🧢 emoji.
Audit Metadata