Scanned skills

google/skills agent-platform-tuning

Checked the catalogued skill at agent-platform-tuning.

SkillTrust corpus scan 22 September 2026 v0.10.0 via skillsh Verify on GitHub
D AI-triaged 2
GitHub
D Security

D; retained sample includes a high finding · SD-022 · what this rule accepts as a false positive →

D Permissions

D; retained sample includes a high finding · SD-003 · what this rule accepts as a false positive →

A Transparency

A set by no findings on this axis

2 findings
securityhigh SD-022
SKILL.md
permission_hygienehigh SD-003
SKILL.md
3 suppressed by AI triage
securityhigh SD-007 benign_example
scripts/calculate_cost.py

The matched URL appears only in a comment; no outbound request is made.

securityhigh SD-007 benign_example
scripts/monitor_tuning_job.py

The URL is only part of a log message, not an actual outbound network request

securityhigh SD-007 benign_example
scripts/tune_open_model.py

The code only logs a static URL string; no outbound network request is made.