dbx-skill-portfolio-auditor

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow runs scripts/inventory_installed_skills.py and scripts/analyze_skill_inventory.py, which read and summarize outsider-authored third-party skill files (e.g., each installed skill’s SKILL.md, evals/triggers.json, and scripts/* text) from user-specified roots like ~/.agents/skills/./skills, then inject that readable text/derived excerpts into the agent’s LLM context via the generated inventory/analysis report.