The Agent Skills Directory

[SAFE]: The skill acts solely as an instruction set for the agent and does not include any scripts, executables, or hidden commands.
[COMMAND_EXECUTION]: The skill utilizes the permitted Read and Write tools for document processing and does not attempt to execute shell commands or subprocesses.
[DATA_EXFILTRATION]: No network operations or external data transfer mechanisms are present.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external files such as transcripts or articles. Ingestion points: Reads files provided by the user as described in Step 1. Boundary markers: No explicit markers are defined in the instructions to isolate or delimit user-provided content. Capability inventory: The skill uses the Read and Write tools to interact with the local filesystem. Sanitization: No explicit input validation or sanitization steps are defined for the source content. Assessment: The risk is considered low because the agent is directed to follow a specific markdown template and lacks access to the network or high-privilege system commands.

ship-learn-next