repo-audit

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes common shell utilities including ls, find, grep, rm, and mv to perform repository maintenance tasks. These operations are performed within the local repository context and require user approval before the cleanup actions (Phase 4) are executed.\n- [EXTERNAL_DOWNLOADS]: The skill suggests the use of external auditing tools such as depcheck (via npx) and autoflake (via Python). These are established developer tools used for identifying unused dependencies and imports.\n- [PROMPT_INJECTION]: The skill exhibits an attack surface for Indirect Prompt Injection (Category 8) by ingesting untrusted data from the local file system (filenames and paths).\n
  • Ingestion points: Repository file structure scanned via ls and find commands.\n
  • Boundary markers: No explicit delimiters are used to separate file metadata from instructions in the generated audit report.\n
  • Capability inventory: The skill has the capability to delete (rm) and move (mv) files.\n
  • Sanitization: No explicit sanitization or validation of file paths is performed prior to inclusion in shell command templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 12:34 PM