fr-fec-generator

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided accounting data to generate specific file formats, which represents a standard data processing surface for indirect prompt injection. This is a low-risk, inherent characteristic of the skill's utility.\n
  • Ingestion points: Accounting data provided by the user for conversion to the FEC format (SKILL.md).\n
  • Boundary markers: None explicitly defined to separate data from formatting instructions.\n
  • Capability inventory: The agent is instructed to perform file operations, specifically creating tab-delimited text files.\n
  • Sanitization: No specific data sanitization or escaping rules are mentioned beyond compliance with the FEC format.\n- [SAFE]: The skill references trusted official resources (bofip.impots.gouv.fr) for regulatory compliance and does not execute remote code or access sensitive system paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 04:48 PM
Security Audit — agent-trust-hub — fr-fec-generator