meta-spreadsheet-insight

Pass

Audited by Gen Agent Trust Hub on Jun 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from external spreadsheets and uses it to drive subsequent actions.
  • Ingestion points: The read step in SKILL.md extracts data from user-provided Excel workbooks.
  • Boundary markers: The data passed to the analyze step ({{ outputs.read }}) lacks delimiters, markers, or explicit instructions to the LLM to ignore any embedded commands within the spreadsheet content.
  • Capability inventory: The skill possesses write capabilities, including appending new sheets to workbooks (xlsx skill) and saving information to long-term memory (memory skill).
  • Sanitization: There is no evidence of sanitization, filtering, or validation performed on the spreadsheet content before it is passed to the summarization and memory-storage components.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 30, 2026, 01:08 AM
Security Audit — agent-trust-hub — meta-spreadsheet-insight