generate-tech-debt
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs local file management for documentation purposes. Its actions are constrained to a specific file path (/TECH_DEBT.md) and it requires explicit user approval (Step 4) via the AskUserQuestion tool before any modifications are made.
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted user input and output from an external skill dependency.
- Ingestion points: User freeform instructions and the
FINAL.mdfile produced by the/lets-quick-discussionskill. - Boundary markers: No specific delimiters or safety instructions are defined for the ingested data.
- Capability inventory: The skill has the ability to read project files and write to the file system using the
Edittool. - Sanitization: User input and external data are incorporated into the tech debt log verbatim; however, the mandatory user confirmation step and the documentation-focused nature of the file reduce the overall risk.
Audit Metadata