excel-automation

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user data into structured Excel templates.\n
  • Ingestion points: Business data provided by users (e.g., sales records, payroll details) is ingested to populate templates described in SKILL.md.\n
  • Boundary markers: No specific delimiters or safety instructions are defined to separate user data from the agent's formatting logic.\n
  • Capability inventory: The workflow involves generating .xlsx files through an auxiliary xlsx skill, which translates this data into permanent file outputs.\n
  • Sanitization: There is no documentation of input validation or escaping mechanisms to prevent malicious payloads in the input data from influencing the agent's behavior during file creation.\n- [NO_CODE]: The skill consists entirely of markdown documentation, templates, and mathematical formulas for Excel. It does not contain any executable scripts, shell commands, or binary files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 03:41 PM