dbs-report
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local shell operations (mkdir -p) and a Python command string to handle directory creation and generate ISO 8601 timestamps. These are utility tasks integrated into the report generation workflow.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes data from local files, which creates a potential surface for indirect prompt injection if the source archives contain malicious content.\n
- Ingestion points: Local Markdown archive files in the {archive_root}/sessions/{project_name}/ directory.\n
- Boundary markers: No specific boundary markers or instruction-ignoring warnings are used during data merging.\n
- Capability inventory: File system read/write access and local command execution for formatting.\n
- Sanitization: The skill performs direct field extraction and merging without explicit sanitization or validation of the input content.
Audit Metadata