skills/duthaho/skillhub/refactor/Gen Agent Trust Hub

refactor

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands to analyze repository history and calculate code complexity hotspots. Evidence: git log and date commands are used in SKILL.md to identify files with high edit frequency.
  • [COMMAND_EXECUTION]: The skill dynamically identifies and executes test suites as defined in project metadata (e.g., AGENTS.md, manifests, or CI configs) to ensure behavior is preserved during refactoring.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from the repository (git logs, bug reports, and project documentation), creating an indirect prompt injection surface.
  • Ingestion points: git log output, out/dev/bugfix-log.md, and project specs.
  • Boundary markers: The skill uses a structured markdown template (references/brief-template.md) to isolate and present this data for user review before any action is taken.
  • Capability inventory: Shell command execution and file system write access within the local project directory.
  • Sanitization: No specific sanitization or escaping of ingested repository content is mentioned before interpolation into the analysis brief.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 04:21 PM
Security Audit — agent-trust-hub — refactor