sales-f5bot
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses a persistent learnings file that creates an indirect prompt injection surface.
- Ingestion points: Information is ingested from references/learnings.md and processed from user-provided context.
- Boundary markers: No delimiters are specified to distinguish between data and instructions in the learning file.
- Capability inventory: The skill grants the agent the ability to read and append content to references/learnings.md.
- Sanitization: There is no requirement for the agent to validate or sanitize data before appending it to the learnings file.
Audit Metadata