competitor-teardown
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external content (social media posts) which creates a surface for indirect prompt injection.
- Ingestion points: The skill instructs the agent to process "[HANDLE]" and "[paste 5-10 with views/likes/comments]" provided by the user.
- Boundary markers: There are no explicit delimiters or instructions for the agent to ignore potentially malicious commands embedded within the pasted posts.
- Capability inventory: The skill is purely instructional and does not utilize any file-writing, network, or command execution tools.
- Sanitization: No input sanitization or validation is implemented for the external text content.
Audit Metadata