optise-helix-prompt-pack-builder
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion points: Untrusted data enters the agent context through user-supplied fields such as category, ICP, and competitors, as well as bulk prompt inputs in Ingest mode. Boundary markers: There are no explicit delimiters or instructions to differentiate user data from system instructions. Capability inventory: The agent utilizes web_fetch and web search tools to verify URLs and research competitor data. Sanitization: No input validation or instruction filtering is implemented to mitigate malicious payloads in user-supplied strings.
Audit Metadata