`agent_human_loop_disabled`

OWASP ASI02

Agent Human Loop Disabled — a PullGuard finding type. Findings of this type appear in the PR comment, Step Summary, SARIF (GitHub Security tab / IDE viewers), and the HTML report, each with severity, location, and the remediation guidance below.

How to fix

Keep a human-in-the-loop / approval step for high-privilege tool calls low effort

# Before (VULNERABLE): every tool call auto-approved
executor = AgentExecutor(agent=agent, tools=tools, auto_approve=True)

# After (SAFE): require approval for irreversible/high-privilege tools
executor = AgentExecutor(agent=agent, tools=tools)  # keep the default gate
# or restrict auto-approval to a read-only allowlist only

If you must auto-approve, restrict it to a read-only tool allowlist medium effort

Triage

Suppress a confirmed non-issue with a committed .pullguardignore entry (pullguard ignore locally, or comment /pullguard ignore <fingerprint> <reason> on the PR — the fingerprint is printed in the PR comment’s Triage section). Entries support expiresAt for time-boxed snoozes.

Security findings at major or critical severity — and any critical finding — always surface: .pullguardignore cannot hide them. The reviewed paths that keep them visible are acknowledged (reviewed, stays in reports) and, for a confirmed false positive, a reasoned false_positive entry — visible and audited, excluded only from the merge block.