assumption-bounty
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown-based instructions for identifying assumptions and lacks any scripts or tools.
- [SAFE]: No malicious patterns like direct prompt injection, obfuscation, or data exfiltration were found.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided documents, which is a potential surface for indirect prompt injection. However, the risk is negligible as the skill has no executable capabilities or network access.
- Ingestion points: The documents provided by the user for analysis.
- Boundary markers: Absent.
- Capability inventory: None.
- Sanitization: Absent.
Audit Metadata