app-health-check
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses local search and discovery tools including grep, glob, and file read operations to identify issues based on a provided checklist. These operations are restricted to the local filesystem and are appropriate for a security auditing tool.- [COMMAND_EXECUTION]: The skill executes standard system commands to retrieve the current date for report naming purposes. It specifically uses
date +%Ffor bash environments andGet-Datefor PowerShell.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the codebases it audits. - Ingestion points: The agent reads all files within the target project repo using grep and read tools (referenced in SKILL.md and audit-checklist.md).
- Boundary markers: The skill lacks explicit delimiters to separate auditing instructions from the content being audited, although it includes a 'verification' step requiring the agent to confirm findings in context.
- Capability inventory: The skill possesses the ability to read all project files, write new markdown reports to the filesystem, and modify existing code when applying fixes.
- Sanitization: No specific content sanitization or escaping mechanisms are defined for the data extracted during the audit.
Audit Metadata