tech-debt-sprint
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted content from the codebase, such as TODO or FIXME comments, and performs file modifications and command execution based on that content.\n
- Ingestion points: Reads all files and developer comments in the codebase during Phase 1 and 2.\n
- Boundary markers: Lacks delimiters or instructions to ignore embedded commands within the analyzed code.\n
- Capability inventory: Performs file writes for refactoring, file deletions for dead code removal, and executes build/test commands.\n
- Sanitization: No sanitization is performed on the data extracted from code comments before it influences agent actions.\n- [DATA_EXFILTRATION]: The skill accesses and writes to the
~/.claude/projects/directory to store execution telemetry. While intended for internal logging, this directory contains sensitive agent-specific configuration and project state.
Audit Metadata