senior-architect
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHNO_CODEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [NO_CODE] (HIGH): The skill describes critical functionality performed by external scripts (scripts/architecture_diagram_generator.py, scripts/project_architect.py, and scripts/dependency_analyzer.py) that are not provided in the skill package, preventing any verification of the code's safety or logic.
- [PROMPT_INJECTION] (HIGH): High risk of Indirect Prompt Injection (Category 8). 1. Ingestion points: Analyzes project codebases from user-provided paths. 2. Boundary markers: No delimiters or instructions to ignore embedded directives are included. 3. Capability inventory: Possesses 'automated fixes' (file-write access) and command execution capabilities. 4. Sanitization: No evidence of filtering or sanitizing analyzed project content.
- [COMMAND_EXECUTION] (MEDIUM): The skill instructs the agent to run multiple unverified Python scripts and shell commands (npm, pip, docker, kubectl) on the host system.
- [EXTERNAL_DOWNLOADS] (MEDIUM): The workflow requires installing dependencies from unprovided manifest files (package.json and requirements.txt), which can result in the installation of unverified or malicious external packages.
Recommendations
- AI detected serious security threats
Audit Metadata