retro
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas.
Security
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
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
Third-party content exposure detected (high risk: 0.90). The skill explicitly runs git fetch and many git log commands against origin/<default> (e.g., "git fetch origin <default> --quiet" and the multiple "git log origin/<default> --since=..." calls) and reads repository files like TODOS.md and ~/.gstack/greptile-history.md, meaning it ingests arbitrary, user-/third-party authored repo content and commit messages which the agent is required to interpret and which materially influence its analysis and actions.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 1.00). The skill runs git fetch origin and multiple git log commands against origin/<default> at runtime (i.e., the repository URL configured as the 'origin' remote — e.g. git@github.com:org/repo.git or https://github.com/org/repo.git), and it uses the fetched commits/files/TODOS to directly drive the agent's narrative, so remote repo content can directly control prompts/output.
- Repository
- garrytan/gstack
- Commit
c86faa7
- 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.