video-template-frame-light-leak-cinema
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and analyzing external video templates and source materials, which serves as a vector for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Step 1 of the workflow in
SKILL.mdrequires the agent to inspect files, versions, and inputs from the project environment. - Boundary markers: The skill does not provide specific instructions for isolating external content or using delimiters to prevent the agent from following instructions embedded in the data.
- Capability inventory: The skill uses the
sandbase_runtool to execute capabilities based on analyzed inputs, providing a mechanism for injection-driven actions. - Sanitization: There are no defined processes for sanitizing metadata or content from video templates before they influence the agent's logic or tool calls.
Audit Metadata