apex-ai-pm-assistant
Use when the user asks to "use AI for project management", "augment PM with AI", "implement predictive scheduling", "parse status with NLP", or "design ML risk models". Activates when a stakeholder needs to identify AI augmentation opportunities for PM, build predictive scheduling models, automate status report parsing with NLP, design intelligent resource allocation, or create a human-AI collaboration model for project governance.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
The skill instructs the agent to parse status reports and read project management tools/APIs without enforcing selection of specific items, creating an indirect prompt injection risk via external status inputs or Jira/ADO feeds.
- Repository
JaviMontano/mao-discovery-framework
- Revision
15f6e4a
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.