cross-app-shared-auth

Pass

Audited by Gen Agent Trust Hub on Aug 9, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it ingests and processes untrusted data in the form of the user's application codebase with capabilities to modify the environment and execute code. \n
  • Ingestion points: The agent is directed to inspect the user's application codebase to determine framework details and existing authentication patterns (SKILL.md, Step 1). \n
  • Boundary markers: The instructions lack explicit markers to separate user code from agent directives or warnings to ignore embedded instructions within analyzed files. \n
  • Capability inventory: The skill possesses capabilities to modify source code, configure system environment variables, and trigger deployment and verification commands (SKILL.md, Steps 4, 6, and 7). \n
  • Sanitization: There is no mention of sanitizing or validating the content of the files being read before processing them.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 9, 2026, 11:45 AM
Security Audit — agent-trust-hub — cross-app-shared-auth