skills/softspark/ai-toolkit/council/Gen Agent Trust Hub

council

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted user input from arguments and codebase content retrieved via various tools, which is then interpolated into prompts for sub-agents. This constitutes a potential indirect prompt injection surface.
  • Ingestion points: User-supplied decision questions and codebase data retrieved during the context gathering phase (SKILL.md).
  • Boundary markers: The prompt templates for sub-agents do not include explicit delimiters or instructions to ignore embedded commands within the processed data.
  • Capability inventory: Use of Bash, Read, Grep, and Glob for analysis, and the Agent tool for orchestration.
  • Sanitization: The skill does not implement escaping or validation of the input data before it is passed to the sub-agents.
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to search the codebase for relevant tech stacks, dependencies, and patterns. This execution is scoped to context gathering for the architectural evaluation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 06:07 AM
Security Audit — agent-trust-hub — council