The Agent Skills Directory

[SAFE]: No malicious patterns or high-risk behaviors were detected during the analysis. The skill follows its stated purpose of assisting with project build automation.
[DATA_EXFILTRATION]: The skill performs no network requests and uses no tools capable of external communication (e.g., curl, wget). It operates exclusively on local files within the project repository.
[COMMAND_EXECUTION]: Command execution is restricted to the 'git' binary (Bash(git *)) used solely for retrieving version information and commit hashes for inclusion in build artifacts.
[PROMPT_INJECTION]: The skill incorporates a project-specific context mechanism that reads configuration from the .ai-factory/ directory. This is an intended feature to allow customization of build templates based on project needs.
Ingestion points: .ai-factory/DESCRIPTION.md and .ai-factory/skill-context/aif-build-automation/SKILL.md (SKILL.md).
Boundary markers: Absent; the skill is explicitly instructed to let these project-specific rules override default instructions.
Capability inventory: Write and Edit tools are used to modify project configuration files and documentation (SKILL.md).
Sanitization: None; the skill uses these files as trusted configuration for tailoring the build environment.

aif-build-automation