infra-forecast-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external business signals from JSON or CSV files, which represents a potential attack surface for indirect prompt injection if the data is later processed by an LLM.
- Ingestion points: The
run.pyscript reads file content from a user-supplied--inputpath inmain(). - Boundary markers: The current implementation does not define boundary markers or delimiters for the ingested data.
- Capability inventory: The skill performs local file system reads and writes (
Path.read_text,Path.write_text) but lacks network access or arbitrary command execution capabilities. - Sanitization: Input data is parsed as JSON, providing a layer of structural validation, though no content-level sanitization is implemented in the current scaffold.
Audit Metadata