business-investment-advisor
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest content from an external file ('company-context.md'), which could potentially contain malicious instructions intended to manipulate the agent's output.
- Ingestion points: The agent is instructed to read the file in the 'Before Starting' section.
- Boundary markers: No specific delimiters are provided to the agent to distinguish between its instructions and the file content.
- Capability inventory: The skill is restricted to financial calculations and logic; it does not have the ability to execute code or access the network, which limits the potential impact of an injection.
- Sanitization: There is no mention of filtering or validating the ingested content.
Audit Metadata