password-attack

Fail

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: CRITICALINDIRECT_PROMPT_INJECTIONSAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions and associated guides facilitate the ingestion of untrusted data from remote targets, creating a surface for indirect prompt injection attacks.
  • Ingestion points: Data enters the agent context through CeWL crawling target websites and service responses processed by Hydra, Medusa, and Ncrack as seen in guides/credential-stuffing-automation-guide.md and payloads.md.
  • Boundary markers: The provided command templates and scripts lack explicit delimiters or warnings to ignore instructions that might be embedded in scraped metadata or service banners.
  • Capability inventory: The skill possesses extensive capabilities including shell command execution via Bash and network access via WebFetch.
  • Sanitization: There is no evidence of sanitization or validation logic for data captured from target systems before it is integrated into the workspace or wordlists.
  • [SAFE]: Automated security alerts concerning book.hacktricks.xyz were reviewed. This domain is a well-known security documentation resource and the skill references it neutrally for educational methodology without downloading executable code.
Recommendations
  • Contains 3 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 19, 2026, 04:36 PM