zhouwenjie1 6a5543cd1c tools: add skill security scanner with LLM intent review ... Static analysis + LLM-assisted security scanner for agent_skills. Detects dangerous tool usage, prompt injection, credential extraction, data exfiltration, and stealth instructions in skill markdown files. Features: - Tool risk scoring tailored to embedded device capabilities - Regex hard gates (critical findings cannot be overridden by LLM) - LLM intent review (--llm-review) to reduce false positives - Baseline diff mode (--baseline) for CI incremental scanning - 3-level disposition: pass / review / block Usage: python3 scripts/skill_security_scan.py [--llm-review] [--ci] Signed-off-by: zhouwenjie1 <zhouwenjie1@xiaomi.com>		2026-05-12 11:39:57 +08:00
..
add_jira_id.sh	Initial commit	2026-04-11 15:27:58 +08:00
regen_changeid.sh	Initial commit	2026-04-11 15:27:58 +08:00
skill_security_scan.py	tools: add skill security scanner with LLM intent review	2026-05-12 11:39:57 +08:00