review
Pre-landing PR review. (gstack)
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: 0.85). Outsider free text can enter the LLM context via Greptile comment bodies fetched at runtime from GitHub (`gh api .../pulls/$PR_NUMBER/comments` and `/issues/$PR_NUMBER/comments`), which are then read/used for review and reply generation in Step 2.5/5.
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: 0.80). The skill runs git fetch/merge on the user's GSTACK_HOME (the $HOME/.gstack repo) at runtime via "cd \"$_GSTACK_HOME\" && git fetch origin ... && git merge --ff-only origin/$(git rev-parse --abbrev-ref HEAD)" which pulls from the repo's origin remote (the git URL configured for ~/.gstack) and those fetched artifacts are later read/used by the agent (plans, learnings, artifacts), so a remote git URL (origin of ~/.gstack) is a runtime external dependency that can alter prompts/behavior or introduce executable artifacts.
- Repository
- garrytan/gstack
- Commit
a325940
- 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.