integration-partnership-strategy
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes an interactive 'Interview' section to gather business context from the user, which constitutes a potential ingestion point for untrusted data. The risk is assessed as safe because the skill is restricted to generating strategy documentation and lacks executable capabilities—such as file manipulation, network access, or command execution—that could be leveraged by an attacker.
- Ingestion points: User answers to interview questions in
SKILL.md. - Boundary markers: None explicitly defined to isolate user input from the skill's logic.
- Capability inventory: No tools or scripts with executable permissions are included; the skill is intended for high-level strategy and documentation only.
- Sanitization: No input validation or filtering logic is present for user responses.
Audit Metadata