quality-detect-refactor-markers

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a read-only auditor for technical debt tracking. It uses common utilities like grep, find, and date to identify and age markers in the source code.
  • [COMMAND_EXECUTION]: Although the skill utilizes shell commands, the parsing logic for extracting ADR identifiers from source files is constrained to specific numeric patterns (e.g., ADR-(\d+)). This restrictive parsing prevents command injection vulnerabilities that could otherwise arise from processing untrusted file content.
  • [DATA_EXFILTRATION]: No network activity or external communication patterns were identified. The skill's functionality is strictly confined to the local project environment.
  • [PROMPT_INJECTION]: A review of the instructional text and metadata confirms the absence of any patterns intended to override agent behavior, bypass safety guardrails, or leak system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 05:24 PM