Skills
Navigate
skills/xberg-io/crawlberg/serving-the-api/Gen Agent Trust Hub

serving-the-api

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation describes the installation of the crawlberg-cli tool using the cargo install command to enable API serving capabilities.\n- [COMMAND_EXECUTION]: Instructions include running crawlberg serve to start a long-running REST API server and using curl commands to interact with the service on the local loopback address.\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external websites, which could contain malicious instructions designed to influence the behavior of the agent.\n
  • Ingestion points: The POST /v1/scrape and POST /v1/crawl endpoints documented in SKILL.md take a url parameter and process content from that external source.\n
  • Boundary markers: No specific delimiters or instructions for the agent to ignore embedded commands within the scraped content are mentioned in the documentation.\n
  • Capability inventory: The service performs network operations to fetch data from arbitrary external URLs.\n
  • Sanitization: The documentation does not specify any sanitization, filtering, or validation protocols to prevent malicious content from being processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:27 PM
Security Audit — agent-trust-hub — serving-the-api