senior-architect
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on the execution of local Python scripts (
scripts/architecture_diagram_generator.py,scripts/dependency_analyzer.py, andscripts/project_architect.py) to perform its functions, running these via thepythonorpython3command on a user-specified project path. - [PROMPT_INJECTION]: The skill processes untrusted local project data, creating an attack surface for indirect prompt injection where malicious instructions embedded in a project's files could influence the agent's behavior.
- Ingestion points: Local source code and project configuration files (e.g.,
package.json,requirements.txt,go.mod) within the target directory. - Boundary markers: Absent; the skill does not use delimiters to distinguish between untrusted data and system instructions.
- Capability inventory: Execution of shell commands and reading of local files within the project scope.
- Sanitization: Absent; there is no evidence of filtering or validation of content read from the project files before it is processed by the agent.
Audit Metadata