powerview
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data retrieved from Active Directory objects (e.g., user properties, group memberships).
- Ingestion points: Active Directory object attributes (such as
samaccountname,distinguishedname) retrieved via PowerShell functions defined inSKILL.md. - Boundary markers: None present to distinguish AD data from instructional context.
- Capability inventory: PowerShell script execution and function invocation as described in
SKILL.md. - Sanitization: No sanitization or escaping of AD query results is mentioned.
- [COMMAND_EXECUTION]: The skill instructs the agent to dot-source a local script (
. .\PowerView.ps1) to load functions into the PowerShell environment, as seen inSKILL.md.
Audit Metadata