pair-agent
Pair a remote AI agent with your browser. (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 includes an explicit instruction to embed a non-visible marker (<gstack-qid:...>) inside rendered questions (it "doesn't render visibly...") which is a hidden/obfuscated instruction that is not directly related to the /pair-agent purpose and thus constitutes a prompt-injection-style hidden directive.
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 requires the agent to output the full instruction block verbatim (which contains the one-time setup key/session token) and asks the user to provide an ngrok auth token that the agent must insert into a command, forcing the LLM to handle and emit secrets directly.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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 downloads and executes a remote install script at runtime via curl "https://bun.sh/install" and then runs it with bash (BUN_INSTALL flow), which fetches and executes remote code during setup.
- 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.