ai-video-generation
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requests and uses the Bash tool to execute the
infshCLI, which is necessary for its functionality of running remote AI video models. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it passes user-defined prompts and external URLs directly to the CLI tool. 1. Ingestion points: User prompts and media URLs are ingested through the JSON --input argument in
SKILL.md. 2. Boundary markers: No delimiters or ignore-instructions are utilized to wrap untrusted inputs. 3. Capability inventory: The skill utilizes theBash(infsh *)tool to execute commands based on these inputs. 4. Sanitization: There is no evidence of input validation or sanitization in the provided templates.
Audit Metadata