skills/jeremylongshore/claude-code-plugins-plus-skills/setting-up-distributed-tracing/Gen Agent Trust Hub
setting-up-distributed-tracing
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill's configuration in
SKILL.mdgrants broad system access through theBash(cmd:*)tool, which allows the agent to execute any shell command. While necessary for the skill's infrastructure-related tasks, it represents a significant capability. - [PROMPT_INJECTION]: A surface for indirect prompt injection exists due to the skill's core functionality. Ingestion points: The
scripts/instrument_service.pyscript recursively reads and processes files from user-defined paths. Boundary markers: No specific boundary markers or 'ignore' instructions are implemented in the file processing logic. Capability inventory: The skill is granted access to file manipulation tools and unrestricted bash commands. Sanitization: No validation or sanitization of file contents is performed. This configuration could allow maliciously crafted files in the local environment to influence the agent's behavior if their contents are processed into the agent's context.
Audit Metadata