Unverified50% confidenceFactExact time
Agent Skill Publish Gate is a static audit tool containing 7 gates that can pre-check SKILL.md before submission to any platform.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/16/2026
First Seen
Valid until: 1/14/2027
Sources
Related Entities
Related Claims
UnverifiedIndirect prompt injection refers to a skill instructing the model to read a document from the web while malicious instructions are hidden in that document, potentially causing the model to treat external content as a trusted instruction source when processing it.63% similarUnverifiedAgentic coding tools can autonomously read and write files, execute terminal commands, break down tasks and advance them step by step, and require frequent requests for human confirmation to control risk61% similarUnverifiedEmbedding API keys in prompts may lead to leakage through model logs, conversation history, or the training data of third-party models.60% similarUnverifiedThis n8n workflow aggregates four data sources—invoice information, actual delivery records, payment collection records, and follow-up records—uses a code node to find discrepancies, and then lets AI decide whether to send a collection email to the customer.60% similarUnverifiedThis workflow consists of seven steps: form trigger, email validation, GoHighLevel contact deduplication check, automatic contact creation, AI classification routing, opportunity creation by route, and sending a Slack notification.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1043149API
curl https://kongchang.com/api/v1/knowledge/claims/1043149MCP
get_claim(id=1043149)