concept-guard

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_CONTEXT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a mechanism to automatically read and inject architectural constraints from local markdown files into the agent's reasoning context during file edits.
  • Ingestion points: The runtime/scripts/drift-context.sh and runtime/scripts/post-check.sh scripts read sections from CONCEPT.md and PIPELINE.md files located in the project directory when the agent initiates a write or edit operation.
  • Boundary markers: Injected context is prefixed with the file path and section name (e.g., [relative/path/to/spec ## interactions]) but lacks instructions to the model to disregard potential instructions embedded within those data sections.
  • Capability inventory: The agent has permissions to read/write/search files and execute shell commands within its environment.
  • Sanitization: The scripts extract raw text from markdown sections using sed without filtering for potential prompt injection patterns before passing it to the agent's prompt context.
  • [DYNAMIC_CONTEXT_INJECTION]: The skill utilizes the Claude Code hook system to execute bash scripts that dynamically provide context to the agent.
  • Evidence: runtime/hooks/hooks.json defines hooks for SessionStart, PreToolUse, and PostToolUse that execute the provided bash scripts.
  • Logic: drift-context.sh performs an upward directory traversal to find architectural specifications relevant to the file being edited, injecting their content directly into the tool call's output as additionalContext.
  • [COMMAND_EXECUTION]: The skill relies on local shell script execution for its core monitoring and context-injection features.
  • Evidence: The scripts runtime/scripts/session-start.sh, runtime/scripts/drift-context.sh, and runtime/scripts/post-check.sh use standard Unix utilities like find, jq, sed, and awk to analyze the project state and report it to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 11:23 AM