canary
Post-deploy canary monitoring. (gstack)
Security
3 findings — 1 critical severity, 2 medium severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E004: Prompt injection detected in skill instructions
What this means
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
Why it was flagged
Potential prompt injection detected (high risk: 0.80). The skill includes many hidden side-effecting instructions (auto-upgrades, telemetry toggles/logging, creating/committing CLAUDE.md routing, vendoring migration, artifact sync prompts, and even an install-via-curl flow) that are outside the stated read-only canary/monitoring purpose and could modify user repos, settings, or run network installs without explicit, scoped consent.
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). Phase 3/5 uses the browse daemon to fetch live production pages at runtime (`$B goto <url>` / `$B links` / `$B snapshot` / `$B text`), and the resulting page text is ingested into the agent’s LLM context, which can include outsider-authored free text from the target site.
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: 0.90). The skill's setup step will, at runtime when bun is missing, curl and execute the installer script from https://bun.sh/install (curl -fsSL "https://bun.sh/install" -o "$tmpfile" … bash "$tmpfile"), which fetches and runs remote code.
- Repository
- garrytan/gstack
- Commit
070722a
- 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.