partner-channel-conflict
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes a detailed 'Interview' process to collect specific business context from the user, which is then used to synthesize the final Rules of Engagement artifact. This processing of untrusted user input creates a surface for indirect prompt injection. However, the risk is significantly mitigated as the skill lacks capabilities such as file system writing or network operations, limiting the impact to potential output manipulation.
- Ingestion points: User responses to the multi-step interview questions in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or instructions to prevent the agent from following directives embedded within the business context provided by the user.
- Capability inventory: The skill is focused on text generation and does not call any external scripts, binaries, or network-enabled tools.
- Sanitization: No explicit sanitization or input validation logic is described in the workflow.
Audit Metadata