viral-reel-generator
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a 'Raw Dump' method in SKILL.md that instructs the agent to process user-provided notes, articles, or URLs. This ingestion of untrusted data represents a potential attack surface.
- Ingestion points: The workflow encourages users to paste external content and URLs directly into the agent context in the 'Input Handling' section of SKILL.md.
- Boundary markers: There are no instructions for the agent to use delimiters or to treat the external content as untrusted, increasing the risk of the agent following instructions embedded within the provided data.
- Capability inventory: The skill is entirely instruction-based and does not define any allowed tools, scripts, or shell commands in its frontmatter or body, which limits the potential impact of an injection to text output manipulation.
- Sanitization: The instructions do not provide any mechanisms for sanitizing or validating external input before it is processed.
Audit Metadata