full

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs fetching and using external, public resources — e.g., "Docs Check" (run /doc <name> <url>) and "Skill Discovery" (run ./scripts/skillsmp-search.sh "<task type>" --install to pull community skills into 1shot/skills/) — and treats those fetched docs/skills as sources of truth that will influence planning and execution, so untrusted third-party content can materially affect agent behavior.