pentest-hacktricks-finder

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches security research information and technical payloads from the HackTricks wiki domain (book.hacktricks.wiki), which is the primary intended function of the skill.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it processes content from an external community-editable source.
  • Ingestion points: Data is retrieved from the book.hacktricks.wiki domain using the web_fetch tool as described in the Workflow and Fetch and Extraction sections.
  • Boundary markers: The instructions do not define explicit boundary markers or directions for the agent to ignore instructions embedded within the fetched external content.
  • Capability inventory: The skill allows the agent to perform web searches (web_search_exa) and fetch detailed sections from the target wiki.
  • Sanitization: No explicit sanitization or validation is performed on the retrieved content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 06:35 AM
Security Audit — agent-trust-hub — pentest-hacktricks-finder