audit-doctrine

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill operates in a read-only capacity and is designed for documentation and rule analysis. It does not perform file modifications, system changes, or sensitive data exfiltration.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves processing untrusted data from both local files and external websites, which creates a potential surface for indirect prompt injection.
  • Ingestion points: The agent is instructed to read local configuration files (e.g., MASTER.md, detector suites, and exception lists) and fetch live documentation from external services such as Stripe, Linear, and GitHub.
  • Boundary markers: No explicit delimiters or boundary markers are defined in the instructions to isolate processed content from the agent's control logic.
  • Capability inventory: The skill is strictly read-only and does not possess capabilities for command execution, subprocess spawning, file writes, or unauthorized network operations.
  • Sanitization: There are no instructions for sanitizing, escaping, or validating the content retrieved from external documentation or local files before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 11:26 PM