skills/46ki75/skills/kedb/Gen Agent Trust Hub

kedb

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill is comprised entirely of markdown instructions and templates (SKILL.md, kedb-index.md, kedb-template.md). No scripts, binaries, or configuration files that could execute code are present.
  • [SAFE]: Comprehensive analysis of the instructions reveals no malicious patterns, obfuscation, or safety bypass attempts. The skill follows best practices for its intended documentation purpose.
  • [DATA_EXFILTRATION]: No network operations or access to sensitive system paths (like SSH keys or environment variables) were found. The skill only interacts with its internal documentation files.
  • [PROMPT_INJECTION]: The skill handles data from local markdown files, which presents a surface for indirect prompt injection. 1. Ingestion points: Reads content from kedb-index.md and entries/*.md during investigation workflows. 2. Boundary markers: No specific delimiters or instructions to ignore embedded commands are present. 3. Capability inventory: Limited to writing markdown files in the local directory and updating a central index. 4. Sanitization: Content from the files is used directly without specific validation or filtering. Note: This risk is inherent to the skill's function and is mitigated by the requirement for human invocation for all write operations.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 05:15 AM
Security Audit — agent-trust-hub — kedb