The Agent Skills Directory

[SAFE]: Analysis of the skill and the scripts/analyze_capacity.py file reveals no malicious intent. The script uses the pathlib module for safe file system traversal and does not implement dangerous functions like eval() or unauthorized network requests. The requested tools in the metadata are appropriate for a developer-oriented capacity analysis utility.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local file system, creating an attack surface for indirect prompt injection.
Ingestion points: The Analyzer.analyze_directory method in scripts/analyze_capacity.py reads names and metadata from user-specified directory paths.
Boundary markers: The skill does not include specific boundary markers or instructions to the AI to ignore potential commands embedded in file names or metadata.
Capability inventory: The skill is granted access to powerful tools including Bash, Read, Write, and Edit.
Sanitization: No sanitization is performed on the file paths or metadata before they are output in the analysis report, which the agent then processes.

analyzing-capacity-planning