lifecycle-messaging
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from .agents/marketing-context.md, which is a potential surface for indirect prompt injection.
- Ingestion points: The skill is instructed to read the file .agents/marketing-context.md.
- Boundary markers: No explicit delimiters or boundary markers are defined for the ingested context.
- Capability inventory: The skill does not define any dangerous capabilities such as shell execution, file writes, or network access.
- Sanitization: The instructions include a requirement to surface stale or contradictory entries, which serves as a basic validation mechanism.
Audit Metadata