cursor-verify-this
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze evidence from various local surfaces (terminal transcripts, HTTP responses, UI screenshots, and heap snapshots) to verify user claims. This creates an attack surface where maliciously crafted data within those artifacts could attempt to influence the agent's reasoning.
- Ingestion points: External artifacts captured from CLI tools, UI state, API responses, and memory profiles as defined in the 'Workflow' and 'Local Surfaces' sections of SKILL.md.
- Boundary markers: The skill does not provide specific delimiters or instructions to the agent to treat this evidence as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill leverages environment interaction tools such as
control-cliandcontrol-uito gather data. - Sanitization: No specific filtering or sanitization procedures are defined for the captured artifacts before they are processed by the agent.
Audit Metadata