The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it is designed to scan and process content from external documents.
Ingestion points: The skill scanning instructions target all documents in a folder (SKILL.md).
Boundary markers: There are no explicit instructions to use delimiters or ignore embedded commands within the processed documents.
Capability inventory: The skill only performs text extraction and formatting; it lacks tools for network access, file system modification, or command execution.
Sanitization: No filtering or sanitization of the extracted document content is performed.
[SAFE]: No executable scripts, binaries, or command-line instructions are present in the skill.
[SAFE]: No hardcoded credentials, API keys, or access to sensitive local environment files were detected.
[SAFE]: The skill does not perform any network operations or data exfiltration.

timeline-generator