knowledge-base-cache

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation outlines the use of several internal Python scripts, such as scripts/cache_manager.py and scripts/init_knowledge_base.py, to manage the repository and build the cache tiers. It also instructs the user or agent to configure a cron job for daily refreshes to ensure data freshness. These operations are transparently documented as core features of the knowledge management system.
  • [PROMPT_INJECTION]: The skill facilitates an indirect prompt injection surface (Category 8) as it is architected to ingest and process external markdown files for context assembly.
  • Ingestion points: The system reads markdown files from the repository/skills/, repository/docs/, and repository/projects/ directories.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are documented for the context assembly process.
  • Capability inventory: The skill possesses capabilities for local file system access and execution of its internal management scripts.
  • Sanitization: The provided documentation does not specify any sanitization or validation routines for the content retrieved from the knowledge base.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 06:04 PM