atlas-cloud
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts as an interface for processing user-supplied prompts to generate media via external APIs, presenting a standard indirect injection surface.
- Ingestion points: User-provided text prompts and local media files are ingested via the
tool.executefunction inSKILL.md. - Boundary markers: No specific delimiters or instructions to disregard embedded commands in the input data are present.
- Capability inventory: The skill uses
tool.executeto perform network API requests and interacts with the filesystem to read inputs and save outputs in theprojects/directory. - Sanitization: There is no evidence of prompt sanitization or filtering before the data is passed to the generation tools.
Audit Metadata