skills/davidlee/doctrine/audit/Gen Agent Trust Hub

audit

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes several local CLI tools under the doctrine namespace (e.g., doctrine slice conformance, doctrine dispatch candidate status). These tools are used for tracking implementation progress and verifying conformance against design specifications.
  • [PROMPT_INJECTION]: As an audit tool, the skill is designed to ingest and analyze external documentation, code deltas, and verification evidence.
  • Ingestion points: The skill reads design.md, slice-nnn.md, plan.toml, Architectural Decision Records (ADRs), technical specifications, and verification evidence files.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified in this skill's instructions when processing these external files.
  • Capability inventory: The skill executes shell commands via the doctrine CLI and interacts with MCP tools for ledger management (e.g., review_new, review_raise).
  • Sanitization: No explicit sanitization or filtering of external content is described in the workflow instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 02:07 PM
Security Audit — agent-trust-hub — audit