weekly-report
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
az boards work-item showcommand to enrich report data from Azure DevOps (a Microsoft service). This involves executing a CLI tool with arguments derived from parsed git commit history. - [PROMPT_INJECTION]: The skill processes untrusted external data from git commit subjects and full code diffs. This creates an indirect prompt injection surface where an attacker could embed malicious instructions in a commit to influence the automated analysis.
- Ingestion points: Commit messages and git diffs (processed in Step 3 and Step 5).
- Boundary markers: The skill employs a 'dossier' architecture designed to isolate the raw diff processing from the final report generation (Step 7), using fixed-shape records.
- Capability inventory: Includes shell command execution via the Azure CLI and file system writes for report generation.
- Sanitization: The instructions explicitly constrain subagents to describe only behavior visible in the diff and forbid speculation about intent.
Audit Metadata