prompt-injection-test
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of instructional markdown content and does not include any scripts, executable commands, or automated routines.
- [PROMPT_INJECTION]: The documentation discusses prompt injection techniques, intents, and evasions as a subject for security testing. It does not contain instructions designed to bypass the agent's own safety guardrails or override its behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill provides guidance on mapping indirect attack surfaces (such as RAG documents and tool outputs) in target applications. It identifies these as vulnerability points for audit rather than presenting an active threat to the host environment.
- [EXTERNAL_DOWNLOADS]: The skill provides an informational link to the Arcanum PI Taxonomy repository on GitHub. This is a reference to a well-known security research project and does not involve automated code execution or suspicious downloads.
Audit Metadata