content-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data which could potentially contain malicious instructions.
- Ingestion points: The skill instructions specify processing keyword exports, customer call transcripts, survey data, and a local product-marketing-context file.
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded prompts within the ingested data.
- Capability inventory: The skill body is purely instructional and does not include scripts with shell execution, file writing, or network operations.
- Sanitization: No data validation or sanitization steps are defined for the incoming text data.
Audit Metadata