The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill adheres to its stated purpose of providing tax compliance analysis based on provided accounting data.
[INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface through the processing of external accounting files, which is necessary for its tax auditing function.
Ingestion points: Reads company metadata from company.json and accounting records from FEC files.
Boundary markers: Absent; the agent does not use specific delimiters for the content of processed files.
Capability inventory: Limited to file reading and markdown report generation. No dangerous capabilities such as network access or shell execution are present.
Sanitization: No validation or sanitization of the accounting data is performed before processing.

controleur-fiscal