sales-enablement
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to ingest and analyze external data, which creates a potential surface for indirect prompt injection.
- Ingestion points: The agent reads external context files such as
.agents/product-marketing.md, CRM loss reasons, and call transcripts from the environment. - Boundary markers: There are no instructions to use specific delimiters or to disregard potential commands found within the ingested data.
- Capability inventory: The agent has the capability to read files from the workspace and generate complex sales collateral like decks and scripts.
- Sanitization: The instructions do not specify any filtering or sanitization logic for the data being processed.
- [EXTERNAL_DOWNLOADS]: The skill contains informational links to external GitHub repositories, specifically
https://github.com/coreyhaines31/marketingskills/blob/main/tools/REGISTRY.md. These are provided for the user's reference regarding tool integrations and do not represent automated script execution or unauthorized downloads by the agent.
Audit Metadata