frontend-developer

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (ls) to inspect local skill directories (~/.claude/skills/, etc.). This is used for a 'companion check' to verify if recommended skills from the AbsolutelySkilled ecosystem are already installed.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and analyze untrusted user-provided frontend code (HTML, CSS, JS).
  • Ingestion points: Untrusted source code provided by users for performance audits, accessibility reviews, and code quality checks as described in SKILL.md.
  • Boundary markers: None identified; the skill does not use delimiters to wrap the untrusted user code.
  • Capability inventory: The agent has shell access and filesystem read capabilities (via the ls command used in discovery).
  • Sanitization: No evidence of sanitization or validation of user-provided code content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:04 PM
Security Audit — agent-trust-hub — frontend-developer