lov-repo2docs
Warn
Audited by Snyk on Aug 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In lov-repo2docs, the required runtime workflow reads outsider-authored free text by cloning a user-supplied GitHub URL (Step 2 via
git clone) and then ingesting each file’s contents in the incremental authoring loop (Step 6: “Read the unit (the file contents)”).
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill invokes npx to run "create-fumadocs-app@latest" at runtime (scripts/scaffold_docs.py) which fetches and executes remote npm package code, and it also git-clones user-provided repositories such as "github.com/acme/widget" (SKILL.md / README.md) so external repo content is fetched at runtime and directly drives the agent's output; these are runtime external dependencies that can execute remote code or control prompts.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata