sales-talkwalker

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime flow can ingest outsider-authored free text from Talkwalker API search results (e.g., /api/v1/search/results or /api/v1/search/p/{project_id}/results), where the returned title/content/snippets originate from public web/social sources chosen by the user’s query rather than the operating user.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to WebFetch SKILL.md at runtime from URLs like https://raw.githubusercontent.com/sales-skills/sales/main/skills/{skill-name}/SKILL.md, which would inject externally-fetched markdown into the agent's context and directly influence prompts/recommendations (a required step when routing to other sales-* skills).