long-vid
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is susceptible to indirect injection through the $ARGUMENTS variable. 1. Ingestion points: SKILL.md prompt. 2. Boundary markers: Absent; user input is placed directly under the Topic heading. 3. Capability inventory: None; the skill is limited to text generation and lacks access to the filesystem, network, or shell commands. 4. Sanitization: Absent.
- [No Code] (INFO): This skill consists solely of markdown instructions and does not include any executable code, dependencies, or remote scripts.
Audit Metadata