product-tracking-business-case
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from a local file (
.telemetry/product.md) to inform the content of the generated business case. While this is standard for document generation, it creates a surface where malicious instructions in the source file could influence the agent's output. - Ingestion points: The skill reads
.telemetry/product.mdin Step 1 of the Process section inSKILL.md. - Boundary markers: Absent. There are no explicit delimiters or instructions to ignore potential commands embedded within the product model data.
- Capability inventory: The skill is limited to reading local files and writing a markdown document to
.telemetry/business-case.md. It does not perform network operations, shell command execution, or dynamic code evaluation. - Sanitization: No sanitization or validation of the ingested content is specified.
Audit Metadata