genimage
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows security best practices by utilizing local script paths and a dedicated setup command for API credentials instead of hardcoding sensitive information. No malicious obfuscation, persistence, or data exfiltration patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied image descriptions by interpolating them into a shell command argument (--prompt). This creates a theoretical surface for command injection if the agent or script fails to sanitize the input against shell metacharacters like backticks or semicolons.
- Ingestion points: User requests for image generation and editing as described in SKILL.md.
- Boundary markers: Double quotes around the --prompt argument in the script execution template.
- Capability inventory: The skill triggers the execution of a local Python script via a subprocess call.
- Sanitization: The instructions do not define sanitization procedures, relying on the platform's execution environment or the internal logic of the genimage.py script.
Audit Metadata