review-powershell
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill instructions define a purely analytical task: reviewing PowerShell code for stylistic and runtime conventions. No executable scripts, network calls, or sensitive file access patterns were found.
- [INDIRECT_PROMPT_INJECTION]: The skill acts on user-provided PowerShell code, creating a potential surface for indirect prompt injection if the code under review contains malicious instructions directed at the agent.
- Ingestion points: PowerShell code files, directories, or diffs provided as input (referenced in
SKILL.md). - Boundary markers: The instructions do not define specific delimiters or "ignore" markers for the input code blocks.
- Capability inventory: The skill's functionality is limited to textual analysis and the emission of a findings list. It does not include commands for shell execution, network exfiltration, or file modification.
- Sanitization: No explicit sanitization or filtering of the input code content is defined in the instructions.
Audit Metadata