office-hours
YC Office Hours — two modes. (gstack)
Security
1 high severity finding. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
This skill explicitly instructs the agent to include "verbatim user quotes" in a temp-file prompt and to run/print external model calls (codex exec / full verbatim output), which would cause any API keys, tokens, or passwords the user supplied to be embedded and transmitted verbatim — a high-risk secret-exfiltration pattern.
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 skill’s runtime directly ingests outsider-authored free text via WebSearch in “Phase 2.75: Landscape Awareness”, where it searches the web based on the user’s inputs and then reads the top search results to synthesize “what the world thinks.”
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 (NEEDS_SETUP) downloads and then executes a remote install script via curl and bash from "https://bun.sh/install" at runtime, which fetches and runs remote code (SKILL.md:812).
- Repository
- garrytan/gstack
- 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.