onboarding
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill contains only Markdown instructions and reference documentation. No executable scripts, binaries, or automated shell commands were found in the skill package.- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to read local context files such as
.agents/product-marketing.mdto inform its recommendations. This creates a potential surface for indirect instructions to be processed by the agent. Ingestion points:SKILL.md(Initial Assessment section). Boundary markers: None specified. Capability inventory: The skill lacks executable capabilities such as shell access or network operations, limiting the impact to text-based responses. Sanitization: None present.- [SAFE]: All analyzed files and instructions are consistent with the primary purpose of providing user onboarding optimization advice. No malicious patterns, obfuscation, or persistence mechanisms were detected.
Audit Metadata