weekly-report

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to interpolate untrusted user data into structured report templates.
  • Ingestion points: User input regarding weekly accomplishments, blockers, and future plans in SKILL.md.
  • Boundary markers: Absent. The skill does not use delimiters or provide system instructions to ignore embedded commands within the input data.
  • Capability inventory: The skill utilizes the office-mcp server tools (create_docx and fill_docx_template) which likely perform file-system operations.
  • Sanitization: Absent. There is no evidence of filtering or validation of the user input before it is used in the report templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 05:19 AM