The Agent Skills Directory

[SAFE]: The skill functions as a template for generating test plans and PowerShell commands based on conversation context. No malicious behavior, data exfiltration, or obfuscation was detected.
[COMMAND_EXECUTION]: The skill instructs the agent to generate PowerShell commands for the user to execute. These commands are intended for testing project-specific changes and utilize local repository scripts and paths.
[PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it instructs the agent to analyze external data such as changed files and git repository status. 1. Ingestion points: 'changed files, git diff, repository status' as defined in SKILL.md. 2. Boundary markers: No explicit delimiters or ignore-embedded-instruction warnings are specified. 3. Capability inventory: The agent generates copyable PowerShell commands for user execution. 4. Sanitization: No specific sanitization or filtering of the external content is mentioned. This risk is inherent to context-aware summary tools and is mitigated by the fact that commands are generated for human review, not automated execution.

test-changes