skills/sickn33/agentic-awesome-skills/startup-business-analyst-financial-projections/Gen Agent Trust Hub
startup-business-analyst-financial-projections
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill collects untrusted data from the user regarding business models, revenue, and costs, which it then uses to generate a financial report saved to the local filesystem. This creates a surface for indirect prompt injection where malicious content in the input could influence the output file.
- Ingestion points: Business model, starting point, growth/cost assumptions, and funding data provided by the user in Step 1 of the skill.
- Boundary markers: The skill does not define any specific delimiters or boundary instructions to prevent the agent from obeying instructions that might be embedded in the user-provided financial data.
- Capability inventory: The skill is capable of writing files to the local environment, specifically markdown reports as instructed in Step 10.
- Sanitization: No input validation, escaping, or sanitization logic is specified in the skill to filter user-provided content before it is included in the final generated report.
Audit Metadata