perplexity-hardened
Warn
Audited by Snyk on Apr 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's scripts/search.mjs explicitly POSTs user queries to the Perplexity web-search API (https://api.perplexity.ai/search) and formats/prints titles, snippets, and URLs from those third‑party search results, meaning the agent ingests and acts on untrusted public web content returned by the API.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata