jtbd
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied input to generate product analysis reports, which presents a surface for indirect prompt injection.
- Ingestion points: User input is ingested via the
$ARGUMENTSplaceholder inSKILL.md,commands/jobs.md, andcommands/jtbd.md. - Boundary markers: The instructions do not define explicit delimiters or 'ignore' instructions for the processed data.
- Capability inventory: The skill has no active capabilities; it does not use network, filesystem, or shell tools. Its operations are restricted to text generation within the AI's conversation context.
- Sanitization: There is no evidence of input validation or sanitization, though the lack of dangerous tools limits the risk to output manipulation.
Audit Metadata