skills/nordz0r/skills/nextcloud-admin/Gen Agent Trust Hub

nextcloud-admin

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes curl and jq to interact with Nextcloud services. This behavior is consistent with the stated purpose of administrative automation.
  • [EXTERNAL_DOWNLOADS]: Facilitates the retrieval of files from a remote Nextcloud server to the local filesystem using standard WebDAV GET requests.
  • [DATA_EXFILTRATION]: Facilitates the upload of local files to a remote Nextcloud instance via WebDAV PUT requests. The target server is defined by the user through the NEXTCLOUD_URL environment variable.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present due to the processing of remote data:
  • Ingestion points: File contents retrieved via WebDAV and metadata from OCS API JSON responses.
  • Boundary markers: Absent; the skill does not implement delimiters or specific instructions to ignore embedded commands in the processed data.
  • Capability inventory: Network access and file read/write operations via the curl utility.
  • Sanitization: Absent; the skill lacks logic to escape or validate external content before processing. Given this is the primary function of the skill, the risk is considered low and manageable.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 11:42 AM