perplexity

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

• Third-party content exposure detected (high risk: 0.80). The skill's script (scripts/search.mjs) directly calls the Perplexity web API (POST to https://api.perplexity.ai/search) and ingests/prints search results and snippets from the open web as part of its workflow (per SKILL.md and the script), exposing the agent to untrusted third-party content that could contain instructions influencing responses.