Scanned skills
google/skills google-cloud-solution-multi-agent-security
Checked the catalogued skill at google-cloud-solution-multi-agent-security.
D AI-triaged 13
D Security
D; retained sample includes a high finding · SD-007 · what this rule accepts as a false positive →
A Permissions
A set by no findings on this axis
B Transparency
B; retained sample includes a medium finding · SD-007 · what this rule accepts as a false positive →
showing 10 of 13
SKILL.md
SKILL.md
assets/agw-authz-extension.yaml
scripts/hybrid_vpn_agent.py
scripts/register_cloud_run_services.sh
scripts/register_cloud_run_services.sh
scripts/register_cloud_run_services.sh
scripts/validate_ingress_unauth.sh
scripts/validate_ingress_unauth.sh
scripts/verify_egress_policies.py
4 suppressed by AI triage
SKILL.md
The file only contains documentation text about a detected outbound network call, with no actual code or permission grant present.
SKILL.md
The line contains documentation text, not executable code or configuration that would perform outbound network calls.
scripts/enforce_sgp_patch.sh
The script performs a legitimate API call to Google Cloud to enforce SGP, not exfiltration.
scripts/enforce_sgp_patch.sh
The curl command is part of a normal configuration script, not a malicious outbound call.