manage-tech-debt

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill operates on local project documentation and does not perform network operations or access sensitive system files. Its tools are used for standard codebase analysis and documentation management.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it ingests and processes content from external documentation files (ADRs, RFCs, and existing registers) which could potentially contain malicious instructions.\n
  • Ingestion points: Files within the .chalk/docs/engineering/ directory.\n
  • Boundary markers: The instructions do not define specific delimiters or warnings to ignore embedded instructions in the source files.\n
  • Capability inventory: Read, Glob, Write, Grep, and Bash tools are available for processing the data.\n
  • Sanitization: No explicit content validation or sanitization is described for the ingested text.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 08:10 AM
Security Audit — agent-trust-hub — manage-tech-debt