requirements-gathering

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from multiple sources including DevOps work items, mockups, natural language descriptions, existing report files (.rdl, .rdlx-json), and documents to generate a standardized brief. This processing creates a surface where malicious instructions embedded in the source material could influence agent behavior during the requirements extraction process.
  • Ingestion points: Processes external files (Word, PDF, Excel), image content (mockups/screenshots), and remote work item data fetched via the devops-requirements skill.
  • Boundary markers: The skill provides a structured markdown template for output ('Output Contract') but lacks specific instructions for the agent to ignore or delimit potentially malicious natural language instructions found within the source data.
  • Capability inventory: The skill instructs the agent to invoke external skills (devops-requirements), use the dxs command-line tool, and save structured artifacts to the filesystem.
  • Sanitization: The instructions do not define specific sanitization or validation steps for the content extracted from the various source formats.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:52 PM
Security Audit — agent-trust-hub — requirements-gathering