carousel-writer-sms
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates external data from a specific local file to influence its text generation output, creating a potential vector for malicious instructions to be processed.
- Ingestion points: The skill attempts to read
.agents/social-media-context-sms.mdduring the 'Context Check' phase to determine tone and voice. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potentially malicious commands embedded within the context file.
- Capability inventory: The skill is limited to text generation. It explicitly states in the 'Boundaries' section that it does not execute code, access external APIs, or manage files beyond reading the context.
- Sanitization: No evidence of validation or sanitization of the content read from the context file was found.
Audit Metadata