Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed debugging checklist with no executable payload, hidden persistence, or unrelated data access.
Install this if you want the agent to apply a structured root-cause debugging process broadly. Because it includes server deployment and restart guidance, keep normal approval boundaries for real production changes, backups, pushes, and restarts.
Most of the user-facing instructional content is written in Chinese, which implicitly fixes the skill's operating language without stating that users may choose another language. Under the language/locale policy, forcing a specific language without opt-in can be a natural-language policy violation.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
将 SKILL.md 放入你的 skills 目录：
mkdir -p ~/.agents/skills/debug-methodology
cp SKILL.md ~/.agents/skills/debug-methodology/
The README states that after restart, 'all sessions' encountering a debugging scenario will automatically load this methodology, but it does not define concrete trigger phrases, scope boundaries, or exclusion conditions. For a markdown skill description, this is an ambiguous activation condition that could overlap with many common conversations about debugging.
No suspicious patterns detected.