hs-risk
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (HIGH): The instructions in
SKILL.mdrequire executing PowerShell with the-ExecutionPolicy Bypassflag. This bypasses security controls meant to restrict script execution, potentially allowing unauthorized code to run.\n- [COMMAND_EXECUTION] (MEDIUM): Therun.ps1script executes an unverified local Python scripttools/hvdc_ops.py. Without the source for this tool, the skill's full behavior cannot be audited for malicious activity.\n- [PROMPT_INJECTION] (LOW): The skill is vulnerable to indirect prompt injection through its data ingestion process.\n - Ingestion points:
data/items.csvis processed by the Python tool.\n - Boundary markers: No delimiters or safety instructions are used to separate untrusted data from agent logic.\n
- Capability inventory: The skill can execute PowerShell, run Python scripts, and write to the filesystem (
reports/hs_risk.md).\n - Sanitization: There is no evidence of data sanitization or validation in the provided instructions or script.
Recommendations
- AI detected serious security threats
Audit Metadata