skills/ruvnet/ruflo/adr-index/Gen Agent Trust Hub

adr-index

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local script plugins/ruflo-adr/scripts/import.mjs using Node.js via Bash to perform batch indexing of ADR files into the agent's memory. This is the primary intended function of the skill.
  • [PROMPT_INJECTION]: The skill ingests data from local Markdown files, which represents a surface for indirect prompt injection.
  • Ingestion points: Architectural Decision Records located in */docs/adr/ or */docs/adrs/ (SKILL.md).
  • Boundary markers: The content is stored in specific namespaces (adr-patterns, adr-edges), though no specific delimiters for the LLM are described in the instructions.
  • Capability inventory: The skill utilizes the Bash tool for script execution and memory tools for data persistence and search.
  • Sanitization: Mentions an extractAdrRefs() function within the import script to clean references before parsing, which serves to prevent false positives in the index.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 06:38 AM
Security Audit — agent-trust-hub — adr-index