Skills
skills/aj-geddes/useful-ai-prompts/technical-debt-assessment/Gen Agent Trust Hub

technical-debt-assessment

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified in references/code-quality-scanner.md as it ingests local files for analysis.\n- Ingestion points: The scanFile method uses fs.readFileSync to read source code.\n- Boundary markers: Absent; content is not isolated from agent instructions.\n- Capability inventory: The skill has file-read and AST-parsing capabilities (via typescript package) but no network or write access.\n- Sanitization: No sanitization is performed on the ingested code before it is parsed and reported to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 01:51 AM