planning-wsh-improvements

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

• Third-party content exposure detected (high risk: 0.90). The skill's required "Research Process" (Step 2 in SKILL.md) and the RESEARCH-SKILL-TEMPLATE explicitly instruct the agent to perform web search and consult external documentation/past writeups (untrusted public sources) and to synthesize those findings into Agent Skills that will drive generated commands, so third‑party content is fetched and can materially influence actions.