film-screen-capture
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to execute shell commands for capturing screens via a local script (
capture.sh), generating images with thecohubCLI, and performing image format conversions using Python one-liners. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection by fetching and processing external web content for use in image generation prompts.
- Ingestion points: External URLs (e.g.,
neta.art) and user-supplied image assets processed inSKILL.md. - Boundary markers: The skill uses natural language instructions like "EXACTLY the web page" to attempt to control the output, but lacks technical delimiters to separate untrusted data from the system prompt.
- Capability inventory: The skill has the ability to execute shell scripts, write to the file system, and invoke external image generation models.
- Sanitization: There is no evidence of sanitization or validation of the content retrieved from external URLs before it is used in the prompt construction for
gpt-image-2.
Audit Metadata