The Agent Skills Directory

[SAFE]: No malicious patterns detected. The skill provides instructional content and a local Python script for sprint plan auditing.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied JSON data via sprint_planner.py to audit sprint plans. While this represents an ingestion point for untrusted data, the risk is negligible as the script lacks any exploitable capabilities.
Ingestion points: sprint_planner.py reads user-provided JSON files specified via the --input command-line argument.
Boundary markers: No explicit boundary markers or instructions to ignore embedded content are used in the data processing logic.
Capability inventory: The sprint_planner.py script is limited to standard library operations for data validation and text formatting. It contains no subprocess calls, eval/exec functions, file-writing outside of user-specified output, or network operations.
Sanitization: The script utilizes standard json.loads() for parsing, though it does not perform specific sanitization of the string values before rendering them into the Markdown audit report.

sprint-plan