canary
Post-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy". (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: 1.00). The skill embeds numerous unrelated operational commands and prompts (telemetry/brain sync, automatic file edits and commits like adding CLAUDE.md or removing vendored gstack, telemetry logging, and optional publishing of session memory) that change repo state or exfiltrate data and are outside the canary monitoring purpose, so this is a hidden/deceptive instruction risk.
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 directly browses and ingests user-specified public URLs (see Phase 3 Page Discovery and Phase 5 Continuous Monitoring: $B goto <url>, $B links, $B text, and snapshots) and uses that page content to drive alerts and AskUserQuestion decisions, exposing the agent to untrusted third-party content.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 1.00). The skill's SETUP step will fetch and execute a remote install script at runtime via: curl -fsSL "https://bun.sh/install" -o "$tmpfile" && BUN_VERSION="$BUN_VERSION" bash "$tmpfile", which downloads remote code and runs it to satisfy a required dependency for the browse daemon.
- Repository
- garrytan/gstack
- Commit
db9447c
- 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.