canary
Post-deploy canary monitoring. (gstack)
Low
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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
The `canary` skill’s required runtime workflow ingests outsider-authored free text by using the browse daemon to fetch `text` snapshots (Phase 2 baseline capture and Phase 5 continuous monitoring) from user-specified URLs and pages, which can contain arbitrary attacker-controlled 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
The skill's setup step runs curl -fsSL "https://bun.sh/install" to download an install script and then executes it (bash "$tmpfile"), so https://bun.sh/install is fetched and executed at runtime.
- Repository
- garrytan/gstack
- Path
canary/SKILL.md
- Commit
d078622
- 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.