what-context-needed
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data via the
{{question}}template variable. - Ingestion points:
SKILL.mdvia the{{question}}placeholder. - Boundary markers: None present to isolate the user input from the skill instructions.
- Capability inventory: None. The skill does not have any code, network, or file-system writing capabilities.
- Sanitization: No filtering or validation is performed on the user-supplied content.
- [SAFE]: No malicious patterns, command executions, exfiltration vectors, or obfuscation techniques were detected in the analyzed file.
Audit Metadata