Skills
Navigate
skills/noorqureshi/security-skills/recon-js-analysis/Gen Agent Trust Hub

recon-js-analysis

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze JavaScript bundles and source maps from external web applications. Ingesting untrusted third-party code creates a potential surface for indirect prompt injection, as malicious instructions could be embedded within code comments or strings in the analyzed JavaScript files.
  • Ingestion points: JavaScript files (.js) and source maps (.map) fetched from target web applications via tools like katana and subjs.
  • Capability inventory: The skill utilizes tools like linkfinder and jsluice to extract data, and js-beautify for processing.
  • Boundary markers: None specified in the instructions.
  • Sanitization: Not mentioned; the skill assumes the agent will process the raw content of the collected files.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 10:31 AM