intel: ai-security social updates (2026-04-08)#11
Open
kamalsrini wants to merge 1 commit into
Open
Conversation
- model-supply-chain v1.0.1: Add LiteLLM/Telnyx PyPI supply chain attack case study under Step 4 (Inference Dependency Review); add GitHub Actions MCP repo targeting case study; add MCP Shield tool reference; 4 new reference URLs - prompt-injection v1.0.3: Add new 'Confirmed Real-World Exploitation Cases' section with Claude.ai indirect injection → data exfiltration (Oasis Security 2026) as Critical severity calibration case; add Oasis reference URL - agent-security v1.0.3: Add MCP supply chain attack warning in context table; add MCP Shield, GitHub Actions MCP targeting, and Oasis references Sources: - https://www.oasis.security/blog/claude-ai-prompt-injection-data-exfiltration-vulnerability - https://www.wshoffner.dev/blog/anatomy-of-a-github-actions-supply-chain-attack-targeting-mcp-repos - https://blog.pypi.org/posts/2026-04-02-incident-report-litellm-telnyx-supply-chain-attack/ - https://cycode.com/blog/lite-llm-supply-chain-attack/ - https://github.com/GaboITB/mcp-shield
4 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Automated skill updates from social intelligence scan
Findings applied:
Skills updated:
ai-security/model-supply-chain→ v1.0.1: LiteLLM/Telnyx and MCP repo attack case studies under Inference Dependency Review; MCP Shield reference; 4 new URLsai-security/prompt-injection→ v1.0.3: New "Confirmed Real-World Exploitation Cases" section with Claude.ai indirect injection → data exfiltration as Critical severity exampleai-security/agent-security→ v1.0.3: MCP supply chain attack warning in context table; 3 new reference URLsSource: socialsecurityplan.md (2026-04-08)