spec-test-execute

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to generate Markdown reports based on local project data. It enforces directory constraints and requires a pre-context skill to establish the working path, which promotes safe file operations.
  • [PROMPT_INJECTION]: The skill processes external documentation files such as test plans and use cases. While it does not include explicit delimiters to prevent indirect prompt injection from these sources, this is a theoretical risk inherent to document processing skills.
  • Ingestion points: Reads files from {FEATURE_DIR}/verification/ and project/memory/.
  • Boundary markers: Absent; the skill does not specify markers to isolate content from these files.
  • Capability inventory: File write operations for report generation; no network or subprocess capabilities are defined in the provided files.
  • Sanitization: Absent; the skill relies on the agent's internal logic to interpret documentation content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 08:45 AM