harness
What this skill does
Long-running agent framework for task checkpointing, recovery, and dependency management
github/stellarlinkco - Data Exfiltration - 2.7k stars
Threat analysis
Skill info
pkg:github/stellarlinkco/myclaude@f2e75c1?skill=harnessAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
tests/test_hooks.py
os.environ.copy() is used in the build_hook_env function to create an environment for hook subprocesses. While this is a legitimate use case for testing, it could potentially expose sensitive environmCode Injection
Code Injection via local-llm-review
tests/test_hooks.py
The run_hook function uses subprocess.run with [sys.executable, str(script)] and input=json.dumps(payload). This could be a potential vector for code injection if the script or payload is not properlyBadge
Add the Anomity scan badge for harness to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of harness? Report an issue or request a rescan.
