The Agent Skills Directory

[SAFE]: The skill implementation is transparent and restricted to its stated purpose of subcontractor evaluation. It contains no obfuscation or suspicious logic.
[DATA_EXFILTRATION]: No sensitive system files or credentials are accessed. The skill does not perform any network operations to send data externally.
[EXTERNAL_DOWNLOADS]: The skill does not download or execute code from remote sources. It uses the standard pandas library for data operations.
[PROMPT_INJECTION]: No malicious patterns or bypass attempts were found in the instructions or skill body. The skill manages an indirect injection surface safely.
Ingestion points: Processes user-supplied construction data (CSV, Excel, JSON) as described in instructions.md.
Boundary markers: Not present.
Capability inventory: Restricted to filesystem write access for exporting Excel reports in SKILL.md.
Sanitization: The agent is instructed to validate inputs before processing.

subcontractor-prequalification