csv-excel-merger

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 (CSV, Excel, and TSV files) which represents an ingestion surface for malicious instructions aimed at the agent.
  • Ingestion points: Data is read using pandas (pd.read_csv, pd.read_excel) in SKILL.md workflow steps 1 and 3.
  • Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the spreadsheet data.
  • Capability inventory: The skill has the ability to read from and write to the file system using pandas and provides tools for complex data manipulation.
  • Sanitization: While column headers are normalized (lower-cased and stripped), there is no evidence of sanitization for the actual cell content to prevent prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:37 PM
Security Audit — agent-trust-hub — csv-excel-merger