dell-monitor-kvm-setup
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill instructs the agent to read local configuration files within the user's home directory. While these files are intended for the skill's operation, they reside in a sensitive location (~/.config/).
- Evidence: Accesses
~/.config/AgentDesk/workstation/monitor-kvm-setup.mdand~/.config/AgentDesk/workstation-root.txt. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by reading external data without proper boundaries or sanitization.
- Ingestion points: The skill reads workstation details from local files.
- Boundary markers: Absent; there are no instructions to the agent to disregard potential prompts within the ingested file content.
- Capability inventory: The skill is capable of reading and potentially writing to the user's workstation inventory.
- Sanitization: Absent; no validation is performed on the data read from the local files.
Audit Metadata