codex
OpenAI Codex CLI wrapper — three modes. (gstack)
Security
2 findings: 1 critical severity, 1 high 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
The skill instructs the agent to embed an invisible machine-readable marker (`<gstack-qid:...>`) into AskUserQuestion text that "doesn't render visibly" so hooks can auto-decide — a hidden/obfuscated instruction that modifies user-visible output and is deceptive relative to the skill's outward purpose.
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
The skill explicitly tells the agent to read and embed full plan files and diffs into prompts sent to Codex (and to present Codex's output verbatim), which forces the LLM to handle and potentially emit any secrets contained in those files.
Low
Low-risk findings.
1 low severity finding. 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
In `/codex` consult mode, the skill parses the user-provided message as a prompt (including any prompt text the outsider authors) and embeds it directly into the Codex execution prompt via `codex exec "<prompt>"`, which the LLM then ingests as free text at runtime.
- Repository
- garrytan/gstack
- Path
codex/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.