Our AI-agent scanner got it backwards. Here’s what we fixed in v1.1

Description and use

In v1.1, Agent PreShip Guard fixed false positives and added AG008 to detect model‑chosen destructive calls without approval.

Problem

The Agent PreShip Guard GitHub Action incorrectly flagged a safe read‑only uptime check (false positive) and missed a destructive model‑chosen delete operation (false negative).

Outcome

After updating to v1.1, the action correctly flags only the unsafe model‑chosen destructive call and no longer mislabels a safe shell command.

Workflow

• 1. Create a GitHub repository with the Agent PreShip Guard action.
• 2. Add a workflow file (.github/workflows/agent-guard.yml) that checks on pull_request and push events.
• 3. Configure the action to scan the repository path and fail on high severity findings.
• 4. Run the workflow; inline PR annotations show findings.
• 5. Update the action to v1.1 to correct false positives and add new rule AG008.

Evidence

== Agent A ::error AG001 Model/LLM output passed to shell ::warning AG004 shell=True in tool code Agent PreShip Guard: 1 high, 1 medium findings. == Agent B Agent PreShip Guard: 0 high, 0 medium findings.

Source

== Agent A ::warning AG004 shell=True in tool code Agent PreShip Guard: 0 high, 1 medium findings. == Agent B ::error AG008 Model output selects a destructive call with no approval gate Agent PreShip Guard: 1 high, 0 medium findings.

Source