skills/nasrulhazim/claude/project-faq/Gen Agent Trust Hub

project-faq

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exposes an Indirect Prompt Injection surface (Category 8) by processing untrusted data from project repositories to generate documentation.\n
  • Ingestion points: The skill reads CLAUDE.md, README.md, package.json, composer.json, and all project files across repositories provided by the user via filesystem paths.\n
  • Boundary markers: The instructions lack explicit delimiters or safety prompts to ensure the agent treats ingested codebase content as data rather than instructions during synthesis.\n
  • Capability inventory: The skill utilizes file system read and write tools to explore codebase structures and output multiple documentation files.\n
  • Sanitization: No logic is present to sanitize, escape, or validate content extracted from the codebase before it is interpolated into the generated FAQ documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 11:24 AM
Security Audit — agent-trust-hub — project-faq