frontend
What this skill does
Frontend design and performance auditing
github/code-yeongyu - Tool Misuse - 67.6k stars
Threat analysis
Skill info
pkg:github/code-yeongyu/oh-my-openagent@ee81ab7?skill=frontendAssessments (3)
Tool Misuse
Tool Misuse via local-llm-review
scripts/perfection/lighthouse-audit.py
The script uses `uv run --script` with a shebang line `#!/usr/bin/env -S uv run --script` which could be a vector for unexpected behavior if `uv` is not properly secured or if the script is executed iObfuscation
Obfuscation via local-llm-review
scripts/perfection/lighthouse-audit.py
The `LIGHTHOUSE_RUNNER_JS` string is obfuscated and contains a partial script that may be used to execute arbitrary code via `subprocess.run` with `node` and `require` statements, which could be a potRemote code execution
Remote code execution via anomity-rules model-disputed
scripts/perfection/lighthouse-audit.py
# curl -LsSf https://astral.sh/uv/install.sh | shBadge
Add the Anomity scan badge for frontend to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of frontend? Report an issue or request a rescan.
