perplexity-search
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the open web through search results.
- Ingestion points: Data enters the agent's context through the JSON output of the
https://pplx.x402.paysponge.com/searchendpoint, which includes page content and snippets from the web (referenced inSKILL.mdworkflow). - Boundary markers: The instructions do not define clear boundary markers or provide explicit instructions for the agent to ignore commands embedded within the search results.
- Capability inventory: The agent is tasked with synthesizing this data into a cited brief. While the skill does not autonomously execute dangerous scripts after ingestion, the resulting brief influences the agent's final response to the user.
- Sanitization: No sanitization or filtering of the retrieved web content is performed before interpolation into the agent's prompt context.
Audit Metadata