yzr-multi-agent-context

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires the agent to execute local Python scripts (scripts/precheck.py and scripts/coverage.py) and standard shell commands (grep, rm -rf) within the project directory. These are used for project analysis, verification, and cleaning up temporary migration files.
  • [SAFE]: The skill's scripts utilize yaml.safe_load() for processing file metadata, which prevents potential arbitrary code execution vulnerabilities during data deserialization. The workflow is transparent, scoped to the project root, and consistent with documented documentation management tasks.
  • [PROMPT_INJECTION]: The skill includes instructional directives like "Force Read instructions" to ensure the agent processes specific context files. These are documented architectural requirements for the multi-agent format and do not attempt to bypass safety filters or override agent behavior maliciously.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 04:01 AM
Security Audit — agent-trust-hub — yzr-multi-agent-context