ai-storyboard-generator
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the external package from the author's repository on GitHub (github.com/beatra-ai/ai-storyboard-generator-skill). The installation process uses a specific commit hash (4736c45) and tree hash (51baed5) to ensure the integrity of the downloaded content.
- [REMOTE_CODE_EXECUTION]: Instructs the agent to execute downloaded Python scripts, including authorize.py and mcp_client.py. These scripts perform network operations and manage local credentials.
- [DATA_EXFILTRATION]: Transmits user-supplied data, such as prompts and media, to the author's hosted service at mcp.beatra.ai. The skill also sends telemetry data, including the system hostname, agent platform, and installation reference, to api.beatra.ai.
- [CREDENTIALS_UNSAFE]: Saves a bearer token for the Beatra service in ~/.beatra/credentials.json. The skill sets restrictive file permissions (0600) for this directory and file.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data which could theoretically contain malicious instructions.
- Ingestion points: User-provided script, scene, or ad brief text processed in SKILL.md.
- Boundary markers: None explicitly defined in the documentation.
- Capability inventory: The skill has capabilities for network communication (HTTPS), file reading (media uploads), and writing configuration data.
- Sanitization: No specific sanitization or validation logic for the input content is described in the skill documentation.
Audit Metadata