write-like-me
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external chat platforms which can lead to indirect prompt injection attacks.
- Ingestion points: The skill instructions recommend reading conversations using tools like
slack_read_channelandslack_read_threadin SKILL.md. - Boundary markers: There are no explicit instructions to ignore or isolate potential commands embedded within the chat history being read.
- Capability inventory: The skill's primary purpose is to draft and potentially send messages to Slack or other chat interfaces.
- Sanitization: No evidence of input sanitization or validation of the retrieved chat content is present.
Audit Metadata