Ops Data Manager

Pass

Audited by Gen Agent Trust Hub on Mar 3, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No security threats or malicious patterns were identified. The skill is consistent with its stated purpose of managing table data.
  • [NO_CODE]: This skill consists entirely of markdown-based instructions for the agent and does not ship with any scripts, binaries, or external dependencies.
  • [PROMPT_INJECTION]: The skill's data-handling capabilities present a standard indirect prompt injection surface. 1. Ingestion points: User-provided values for table rows and cells in the 'rows' and 'value' inputs. 2. Boundary markers: No explicit delimiters are used to isolate untrusted data in the action payloads. 3. Capability inventory: Uses the 'ops_tables' capability via actions like 'add_ops_rows' and 'update_ops_cell'. 4. Sanitization: The instructions include validation for column names and data types, though not for content strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 3, 2026, 11:38 AM