harness-inspect

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is provided by Adobe, a trusted developer. Its functionality focuses on repository auditing, which is a legitimate and safe activity.
  • [COMMAND_EXECUTION]: Instructions in the skill and its reference files direct the agent to execute standard repository checks such as make check, make test, and ls -la. These commands are used to verify the integrity and status of the harness within the local development environment.
  • [DATA_EXFILTRATION]: The auditing prompts instruct the agent to identify entry points and environment variables referenced in source code to verify documentation coverage. This inspection is local and does not include any mechanism for data transmission to external or untrusted servers.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and guides from official Adobe GitHub repositories and agentskills.io. These sources are recognized as safe and are documented neutrally as per security protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 01:16 AM
Security Audit — agent-trust-hub — harness-inspect