The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected in the provided skill files.
[EXTERNAL_DOWNLOADS]: The skill references and fetches documentation from official vendor-controlled domains including commercengine.io and llm-docs.commercengine.io, as well as the vendor's GitHub repository.
[PROMPT_INJECTION]: The skill documents interfaces that ingest untrusted user data (email addresses and profile details), creating a potential surface for indirect prompt injection.
Ingestion points: Parameters for loginWithEmail, loginWithPassword, and updateUserDetails in SKILL.md.
Boundary markers: No explicit boundary markers or delimiters are defined in the documentation for these inputs.
Capability inventory: The skill declares permission to use the Bash tool.
Sanitization: No specific sanitization or validation routines are detailed in the provided code snippets.

ce-auth