drift-audit

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local shell scripts ./scripts/verify-all.sh and ./levels/L2-ceremonies/scripts/check-drift.sh. These are standard project-local scripts used for linting, testing, and documentation verification.
  • [PROMPT_INJECTION]: There is a potential for indirect prompt injection because the skill requires the agent to ingest and analyze untrusted data from recent pull requests.
  • Ingestion points: Content from recent pull requests (Instructions 3 and 4) enter the agent's context during the audit process.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the PR code or descriptions.
  • Capability inventory: The agent is authorized to execute local scripts (Instruction 1 and 2), modify local configuration files such as CLAUDE.md and AGENTS.md (Instruction 5), and interact with external APIs to create GitHub issues (Instruction 6).
  • Sanitization: There are no documented steps for the agent to sanitize or validate the external PR data before acting on it.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 08:20 AM
Security Audit — agent-trust-hub — drift-audit