The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown instructions and structural templates. There are no scripts (Python, Node.js, Shell), executables, or configuration files that could be used for malicious purposes.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to ingest external data (feature specifications and quality requirements), it lacks any execution capabilities. The output is a formatted Markdown report. The ingestion surface is limited to analysis, and there are no tool calls or system commands that could be subverted by malicious input in the source documents.
[SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or persistence mechanisms was found. The skill adheres to its stated purpose of framework design and includes explicit scope constraints preventing model inference or live endpoint access.

ai-evaluation