The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes development tools locally to perform code validation.
Evidence: scripts/validate_vue.py invokes npx vue-tsc and stylelint via a wrapper that uses subprocess.run(shell=False).
Security Context: The use of shutil.which and shell=False mitigates common command injection vectors.
[INDIRECT_PROMPT_INJECTION]: The skill's workflow creates a surface for indirect prompt injection by reading and acting upon tool output generated from user-controlled files.
Ingestion points: Tool output from vue-tsc and stylelint in scripts/validate_vue.py.
Boundary markers: None identified in the script output.
Capability inventory: The agent can execute commands and is directed to perform file writes to resolve linting issues.
Sanitization: No sanitization is performed on the tool output before it is returned to the agent context.

primevue-openprops-architect