prioritize-assumptions
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows standard instructional patterns for product management tasks. It does not attempt to execute code, access sensitive files, or exfiltrate data.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external assumptions and research data provided by the user. While this creates an ingestion surface for potentially malicious instructions hidden in data, the skill lacks dangerous capabilities such as network access or shell execution that would enable an attack.
- Ingestion points: Processes user-provided assumptions and research files.
- Boundary markers: None present.
- Capability inventory: Limited to generating text and saving markdown files.
- Sanitization: No explicit sanitization of input data is defined.
Audit Metadata