skills/nulfrog/skills/decision-review/Gen Agent Trust Hub

decision-review

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Uses git diff to identify changes in the decision documents within the repository.
  • [COMMAND_EXECUTION]: Executes project-specific typechecking and test suites to ensure codebase integrity after automated edits.
  • [INDIRECT_PROMPT_INJECTION]: Analyzes untrusted project documentation and source code to find contradictions.
  • Ingestion points: Reads decision documents from docs/adr/, GLOSSARY.md, and references in GLOSSARY-MAP.md.
  • Boundary markers: Employs specific prompts for sub-agents with word-count limitations to scope the analysis.
  • Capability inventory: Capable of modifying files and running local shell commands for testing.
  • Sanitization: Relies on instructional scoping and structural separation of sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 12:10 PM