The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run several local Python scripts (architecture_diagram_generator.py, project_architect.py, and dependency_analyzer.py) to perform project analysis. Notably, the 'Project Architect' script claims to provide 'automated fixes', which indicates a high-privilege capability to modify the user's source code.
[EXTERNAL_DOWNLOADS]: The development workflow documentation includes instructions to run npm install and pip install -r requirements.txt. These commands download and install third-party dependencies from public registries that are not explicitly versioned or verified within the skill's instructions.
[PROMPT_INJECTION]: The skill contains a vulnerability surface for indirect prompt injection because it is designed to ingest and process untrusted data from external project files.
Ingestion points: The skill reads file content from user-specified directories using analysis scripts (e.g., python scripts/project_architect.py <target-path>).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between the skill's instructions and potentially malicious instructions embedded in the analyzed code.
Capability inventory: The skill has the capability to execute shell commands and modify the filesystem via Python scripts.
Sanitization: No sanitization or validation of the ingested codebase content is documented before it is processed or used to generate automated fixes.

senior-architect