mapping-attack-techniques

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow here is described as selecting/mapping technique IDs/names and loading the first-party secskills-core/ttp-index.json, with only optional “Reading External Sources” via curl as Markdown; outsider-provided free text is not inherently ingested by this router workflow unless the user explicitly fetches it.