companify-cfo
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting content from multiple local markdown files to generate financial reports.
- Ingestion points: The agent reads content from
.companify/progresso.md,company/business-model.md,company/revenue.md, andcompany/operations.md. - Boundary markers: Absent. The instructions do not provide explicit delimiters or warnings to ignore instructions embedded within the ingested data.
- Capability inventory: The skill is capable of reading project files and writing the finalized model to
company/finance.mdand metrics to.companify/metrics.md. - Sanitization: Absent. There is no evidence of filtering or validation of the content processed from external files.
Audit Metadata