The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to invoke local Python scripts, generate_filename.py and md_to_xmind.py, to handle utility tasks like generating timestamped filenames and converting Markdown files to the XMind format.
[DATA_EXFILTRATION]: The skill incorporates functionality to fetch content from external URLs (such as Feishu documents) using the fetch-doc tool to ingest requirement details. This involves network operations to access user-specified remote resources.
[PROMPT_INJECTION]: The skill processes requirement documents provided by users, which constitutes a surface for indirect prompt injection. If an input document contains malicious instructions, the agent may interpret them as part of its operational flow.
Ingestion points: Requirement documents provided as text strings, local file paths, or remote URLs.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat input data as non-executable text.
Capability inventory: The agent possesses capabilities to execute shell commands and perform file system write operations.
Sanitization: There is no defined process for sanitizing or filtering instructions that might be embedded within the processed requirement documents.

general-testcase