viral-generator-builder
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION] (SAFE): No attempts to override agent instructions or bypass safety filters were detected.
- [DATA_EXFILTRATION] (SAFE): The skill does not perform network operations or access sensitive local files.
- [REMOTE_CODE_EXECUTION] (SAFE): No external script downloads or piped command executions are present.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill describes patterns for ingesting untrusted user input (names, quiz answers, photos) to generate results. While it lacks explicit sanitization guidance, it is an instructional design guide rather than an active tool, presenting minimal risk to the agent itself.
- Ingestion points: User input fields defined in 'Input Design' (SKILL.md).
- Boundary markers: Absent in provided code snippets.
- Capability inventory: None; the skill provides design patterns only.
- Sanitization: Not mentioned in the provided patterns.
Audit Metadata