The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified. The skill operates within the local project directory and performs expected static analysis tasks.\n- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute git log for the purpose of identifying files modified since a specific date. This is a standard development workflow and does not involve passing unvalidated user input to the shell.\n- [PROMPT_INJECTION]: The skill processes content from untrusted Markdown and YAML files, which constitutes a potential surface for indirect prompt injection. The risk is mitigated by the skill's logic, which focuses on extracting specific data points (stats, values, formulas) for comparison rather than executing narrative content.\n
Ingestion points: Markdown files in design/gdd/ and the registry file design/registry/entities.yaml.\n
Boundary markers: None identified in the grepping or reading instructions.\n
Capability inventory: Reading and writing/editing local files, and metadata retrieval via Bash.\n
Sanitization: No specific escaping or validation is performed on the content extracted from the documents before it is presented to the agent.

consistency-check