tech-debt-analyzer
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted codebase content (source code and configuration files) which is then processed during the 'AI-Augmented Analysis' phase. This creates a surface for indirect prompt injection where malicious comments or strings within the analyzed project could attempt to influence the agent's debt assessment or remediation planning.
- Ingestion points: Reads all source code files and dependency manifests in the target project directory.
- Boundary markers: No explicit delimiters or instructions are used to separate untrusted codebase content from the analysis instructions.
- Capability inventory: The skill has permissions to read local files, list directories, and write JSON baseline files to
~/.claude/tech-debt/. - Sanitization: The reporting template (
templates/dashboard.html) includes a JavaScript helper (escH) to escape content for HTML display. - [DATA_EXPOSURE]: The skill maintains a local history of technical debt scans by storing JSON baselines in
~/.claude/tech-debt/. This directory is used exclusively for the skill's own persistence and state management.
Audit Metadata