brightdata-local-search

Warn

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires cloning an external repository from GitHub (https://github.com/yaronbeen/unfancy-search.git) to provide the search functionality.- [COMMAND_EXECUTION]: The setup and usage instructions involve executing shell commands, including 'git clone', 'pnpm install', 'pnpm dev', and 'docker compose up', which execute code from the external repository.- [INDIRECT_PROMPT_INJECTION]: The agent processes results from web searches, which could contain instructions designed to manipulate the agent's behavior.
  • Ingestion points: The agent retrieves content from the local API at '/api/search-status/{jobId}' as described in SKILL.md.
  • Boundary markers: There are no instructions to the agent to treat search results as untrusted data or use delimiters to separate instructions from data.
  • Capability inventory: The skill uses 'curl' to interact with the local API and 'jq' to process the resulting JSON data.
  • Sanitization: No sanitization or filtering mechanisms are described for the search result content before it is used by the agent to ground responses.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 16, 2026, 06:46 AM
Security Audit — agent-trust-hub — brightdata-local-search