guard-review-qbr
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection due to its core function of processing untrusted external data.
- Ingestion points: Workflow Step 1 in
SKILL.mdand Rule 1 inreferences/input-rules.mdinstruct the agent to accept and process unstructured data from multiple external sources, including CRM exports, conversational notes, meeting transcripts, and uploaded PDF documents. - Boundary markers: The instructions do not define explicit delimiters (e.g., XML tags or unique markers) to isolate untrusted content, nor do they include specific warnings for the model to ignore embedded instructions within that content.
- Capability inventory: The skill is capable of generating narrative text, talking points, and triggering the creation of a presentation file (PPTX). It does not have access to the shell, network, or sensitive file system paths.
- Sanitization: There is no evidence of input validation, filtering, or escaping of the ingested data before it is incorporated into the prompt context.
Audit Metadata