perplexity-web-research

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches content from the web via the Perplexity API, which could potentially contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: Search results and reasoning outputs from the llm CLI are returned directly to the agent's context.
  • Boundary markers: The provided instructions do not specify the use of delimiters or 'ignore' instructions to wrap external data.
  • Capability inventory: The skill has access to the Bash tool to perform CLI operations.
  • Sanitization: There is no evidence of specific filtering or sanitization of the remote API response before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of external components, specifically the llm CLI and the llm-perplexity plugin. The setup documentation (references/setup.md) correctly points users toward official package registries and repositories.
  • [COMMAND_EXECUTION]: The skill operates by executing the llm command with various model flags. The use of allowed-tools: Bash(llm:*) in the frontmatter is a defensive configuration that restricts the agent's use of the Bash tool specifically to the intended utility.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 08:33 AM
Security Audit — agent-trust-hub — perplexity-web-research