forecast
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to load sales data from a local file path (
.agents/sales-context.md) which represents a potential surface for indirect prompt injection if that file contains untrusted content. \n - Ingestion points: The skill explicitly instructs the agent to check for and load
.agents/sales-context.mdfrom the project root. \n - Boundary markers: Absent; there are no specific instructions or delimiters provided to the agent to mitigate potential malicious instructions within the context file. \n
- Capability inventory: The skill's functionality is limited to analytical reporting and mathematical calculation; it contains no network communication, file system modification, or shell execution tools. \n
- Sanitization: Absent; the skill assumes the context file contains valid sales data.
Audit Metadata