knowledge-base

Pass

Audited by Gen Agent Trust Hub on Nov 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill enables the ingestion of untrusted external content (from files and web pages) into the agent's context through the import and add commands. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the knowledge base.
  • Ingestion points: External data enters the system through the --from flag in the import command (which reads files or web content via the host tool) and is saved as drafts in tmp/knowledge-base/drafts/.
  • Boundary markers: The skill uses Markdown with structured YAML frontmatter to separate metadata from content. The SKILL.md file contains explicit instructions to the assistant to treat this data as 'reference material, not instructions.'
  • Capability inventory: The skill script knowledge-base.cjs can write Markdown files to the project's documentation directory (docs/knowledge-base/) and update project indexes. It also invokes the $prompt-enhance tool.
  • Sanitization: The skill includes a built-in security validator that scans all ingested content for 'flagged lines.' It identifies and blocks patterns such as instructions to ignore rules, access credentials (e.g., ~/.ssh, .env), or execute shell scripts. This serves as a strong internal guardrail against the injection surface.
  • [PROMPT_INJECTION]: Heuristic detections of 'ignore instructions' patterns in references/pack-format.md are false positives. The file is a technical specification for a security validator; it contains examples of malicious phrases (e.g., 'ignore previous instructions') to explain how they are detected and blocked by the tool's logic. These are descriptive mentions, not active injection attempts.
  • [COMMAND_EXECUTION]: The skill relies on a local Node.js script (knowledge-base.cjs) to manage the knowledge base. This script performs administrative tasks such as indexing, searching, and validating packs. All write operations performed by this script require an explicit --apply flag, which the agent is instructed only to use after the human user has confirmed the specific changes via the host's question tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 10, 2026, 08:16 PM