wait-what
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process the previous message in the conversation history ('Stop. That last message did not land — re-pitch it').
- Ingestion points: The agent context includes the previous message which may contain untrusted data.
- Boundary markers: The instructions do not define specific delimiters or 'ignore' instructions for the content being processed.
- Capability inventory: The skill specifies 'disable-model-invocation: true' in the frontmatter, which prevents the agent from calling tools or other models.
- Sanitization: No explicit sanitization or filtering of the input content is defined.
Audit Metadata