rw-generate-image

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts external reference images via URLs, creating a vulnerability surface where adversarial image data could attempt to influence the agent's logic or downstream tasks.
  • Ingestion points: Remote URLs provided via the --reference-images parameter in SKILL.md.
  • Boundary markers: No specific delimiters or boundary protections are implemented for the injected URLs.
  • Capability inventory: The skill has the ability to perform network requests to the Runway API and write image files to the local file system.
  • Sanitization: The documentation notes reliance on the API's internal safety filters (e.g., SAFETY.INPUT.*).
  • [COMMAND_EXECUTION]: The skill executes local Python scripts using the uv run command. While restricted to the scripts/ directory, this mechanism executes logic that interacts with both the local filesystem and the network.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 10:31 AM
Security Audit — agent-trust-hub — rw-generate-image