flowy-film
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, such as scripts, stories, and ad briefs, which could contain instructions aimed at overriding agent behavior or manipulating the generative output.
- Ingestion points: The skill processes user-provided one-line ideas, scripts, and ad briefs (SKILL.md). It also accepts user-supplied reference URLs for character and setting constants (Phase 1 execution).
- Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore instructions embedded within the user-provided scripts or descriptions.
- Capability inventory: The skill utilizes several powerful generative tools (generate_image, generate_video, generate_audio) and project management commands (create_node, start_render) across its execution phases.
- Sanitization: The skill lacks any defined validation, filtering, or sanitization steps for the input data before it is interpolated into the generation prompts.
Audit Metadata