tech-selection-research

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to perform "multiple WebSearch/WebFetch calls" and to "verify with current sources" using the Source Hierarchy (including Tier 3 items like tutorials, community comparisons and forum discussions) — i.e., the skill requires fetching and interpreting public, user-generated web content as part of its decision workflow (see "Decision Pack" note and "Source Hierarchy" in SKILL.md/references), which can materially influence recommendations.