googlesheets-automation

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its ability to read external spreadsheet content while having broad modification and deletion capabilities.
  • Ingestion points: Untrusted data is retrieved from external sources using tools such as GOOGLESHEETS_BATCH_GET, GOOGLESHEETS_VALUES_GET, and GOOGLESHEETS_LOOKUP_SPREADSHEET_ROW in SKILL.md.
  • Boundary markers: There are no defined delimiters or instructions to prevent the agent from executing commands that might be embedded within the spreadsheet data.
  • Capability inventory: The skill provides access to several sensitive tools, including GOOGLESHEETS_BATCH_UPDATE, GOOGLESHEETS_UPSERT_ROWS, and GOOGLESHEETS_DELETE_DIMENSION, which could be abused if the agent is misled by injected content (SKILL.md).
  • Sanitization: No sanitization or validation processes are described for handling the data ingested from Google Sheets.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 10:57 PM
Security Audit — agent-trust-hub — googlesheets-automation