tdg-personal/knowledge-ops
Knowledge base management, ingestion, sync, and retrieval across multiple storage layers (local files, MCP memory, vector stores, Git repos). Use when the user wants to save, organize, sync, deduplicate, or search across their knowledge systems.
60
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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
This skill's SKILL.md explicitly instructs pulling and ingesting user-generated public content (e.g., GitHub issues/PRs/discussions and "Browser bookmarks" listed under "Layer 1" and "Cross-Source Knowledge Sync"), which the agent is expected to read and use to update memory and drive actions, creating a clear avenue for indirect prompt injection.
Where we found it
GitHub issues, PRs, discussions, release notes
content-type · 2 sites
The plugin instructs the agent to read GitHub issues, PRs, discussions, release notes as Layer 1 sources (line 29) and pull GitHub activity events into the knowledge base during Cross-Source Knowledge Sync (line 114), exposing the agent to third-party content.
SKILL.md
29
GitHub issues, PRs, discussions, release notes
SKILL.md
114
GitHub activity events
Linear issues/projects/docs
content-type · 1 site
The plugin instructs the agent to read Linear issues, projects, and docs as Layer 1 sources (line 29), exposing the agent to content authored by team members or collaborators.
SKILL.md
29
Linear issues/projects/docs
Browser bookmarks
content-type · 1 site
The plugin instructs the agent to pull browser bookmarks during Cross-Source Knowledge Sync, which point to arbitrary external web content that could contain prompt injection payloads.
SKILL.md
113
Browser bookmarks
Claude/ChatGPT/Grok conversation exports
content-type · 1 site
The plugin instructs the agent to ingest conversation exports from Claude, ChatGPT, and Grok during Cross-Source Knowledge Sync, reading external AI conversation content into the knowledge base.
SKILL.md
112
Claude/ChatGPT/Grok conversation exports
- Audited
- Security analysis