The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill includes scripts designed to process user-provided YAML files to generate readiness reports. This creates a potential surface where malicious data within these files could influence the agent's subsequent analysis. However, given the local, diagnostic nature of the tools and the lack of high-privilege operations, the risk is minimal.
Ingestion points: scripts/aims_readiness_score.py and scripts/ai_impact_assessment_checker.py ingest user-supplied files via CLI arguments.
Boundary markers: None explicitly defined to separate script output from agent instructions.
Capability inventory: The tools are limited to local file system read operations and reporting to standard output.
Sanitization: The scripts employ a custom YAML parser that restricts processing to specific assessment keys and logic.

aims-audit