review-powershell
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the analysis of untrusted PowerShell code.
- Ingestion points: The skill ingests source files, directories, or diffs via the
code-scopeinput defined inSKILL.md. - Boundary markers: The instructions lack explicit delimiters or instructions to ignore instructions embedded within the processed code, which could allow comments or strings in the PowerShell scripts to influence the agent's behavior.
- Capability inventory: The skill's primary capability is generating a structured list of findings. It does not possess capabilities for file-write operations, network access, or command execution beyond the analysis context.
- Sanitization: There is no evidence of sanitization or validation of the input code to prevent the injection of malicious instructional content.
Audit Metadata