ig-reply
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied data from Instagram comments, creating a potential surface for indirect prompt injection where malicious instructions in the comments could try to manipulate the agent.
- Ingestion points: Untrusted comment data enters the agent context via user input (text or screenshots).
- Boundary markers: No specific delimiters are used to separate user data from skill instructions.
- Capability inventory: The skill is restricted to text generation and lacks capabilities for network access, file writes, or command execution.
- Sanitization: The skill does not perform sanitization on the ingested comment text.
Audit Metadata