Carousel Post Creator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process "material from the user" to create carousel content. This represents an ingestion point for untrusted data. While there are no explicit boundary markers or sanitization steps mentioned, the skill does not use any high-risk capabilities like network access, file system writes, or command execution, which effectively mitigates the risk of an injection attack causing harm beyond the generated text itself.
- [SAFE]: The skill consists entirely of markdown documentation providing structural advice and templates. It does not include any scripts, dependencies, or hidden commands. No patterns of obfuscation, exfiltration, or persistence were found.
Audit Metadata