shortvideo-script-selfcheck
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed entirely of natural language instructions and YAML metadata. It contains no scripts, binary files, or command-line executions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content (scripts, titles, and descriptions) as part of its primary review function. While this is an ingestion point for untrusted data, the skill lacks any dangerous capabilities that could be leveraged by a malicious payload.
- Ingestion points: User-supplied short video scripts and titles provided for evaluation in the execution steps.
- Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore potentially malicious content within the user-provided data.
- Capability inventory: The skill performs only text analysis and feedback; it has no access to the file system, network, or shell environments.
- Sanitization: No input validation or escaping mechanisms are specified for the processed content.
Audit Metadata