codekb-review

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the codekb command-line utility and standard git commands to manage knowledge entries. These operations are restricted to the local file system within the codekb/knowledge/ directory for the purpose of auditing and versioning knowledge data.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and review markdown files from a local directory. While these files could potentially contain untrusted instructions (Indirect Prompt Injection), the skill's primary purpose is to provide a mechanism for human or automated review and correction of such data, which acts as a mitigation factor. Findings for this category represent an inherent attack surface rather than an active exploit.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 03:54 AM
Security Audit — agent-trust-hub — codekb-review