skills/jablonkai/skills/duv/Gen Agent Trust Hub

duv

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted HTML data from an external website.
  • Ingestion points: HTML content retrieved from several PHP endpoints on statistik.d-u-v.org.
  • Boundary markers: Absent; the instructions do not suggest using delimiters or warnings to ignore instructions embedded in the scraped data.
  • Capability inventory: The skill uses Bash, Read, and WebFetch tools.
  • Sanitization: Absent; there are no instructions provided for sanitizing or validating the retrieved HTML content before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill uses curl and WebFetch to download content from statistik.d-u-v.org. This is essential for the skill's purpose as an ultramarathon database lookup tool.
  • [COMMAND_EXECUTION]: The skill provides detailed curl command examples for retrieving data. While these commands are directed at a specific, legitimate domain, they involve shell execution that requires the agent to safely handle user-supplied search parameters to prevent command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 12:11 AM
Security Audit — agent-trust-hub — duv