wait-what
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a text-formatting utility and lacks any dangerous capabilities. There is no evidence of network operations, credential access, or arbitrary command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by instructing the agent to re-process its previous message, which could be influenced by untrusted data.
- Ingestion points: The skill targets the agent's "last message" (SKILL.md).
- Boundary markers: No specific delimiters or "ignore instructions" markers are present to wrap the re-pitched content.
- Capability inventory: The skill has no identified capabilities for network, shell, or file-system modifications, rendering the injection surface benign.
- Sanitization: No sanitization or escaping of the previous message's content is performed.
Audit Metadata