code-review
Mandatory code reviews via /code-review before commits and deploys
Security
3 findings — 3 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: 1.00). The skill explicitly reads and injects user-generated PR descriptions and issue-tracker references (e.g., "gh pr view --json body" and checking git/PR/issue text in adr-gate.md Step 2e and the ADR draft inputs) into the review/ADR prompt, so untrusted third-party content from GitHub/issue trackers can influence review decisions and tool behavior.
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 includes runtime installation/execution of remote code (e.g., "gemini extensions install https://github.com/gemini-cli-extensions/code-review" and the GitHub Actions step "uses: openai/codex-action@main" which fetches and runs action code), which will be fetched/executed during setup/CI and the skill depends on them for review functionality, so they constitute external dependencies that execute remote code.
W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection)
Why it was flagged
Hidden Unicode characters detected (1 type(s) found)
- Repository
- alinaqi/claude-bootstrap
- Commit
7e5f7a2
- 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.