project-analysis

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses common, non-destructive bash commands to discover project structure and dependencies.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present as the skill processes data from untrusted codebase files.
  • Ingestion points: The skill reads content from README.md, package.json, and other project files via the Read and Bash tools.
  • Boundary markers: No delimiters or specific instructions are provided to distinguish codebase data from system instructions.
  • Capability inventory: The skill has access to the Bash tool, which provides a shell environment for potential command execution.
  • Sanitization: No input validation or content filtering is performed on the ingested project data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 11:52 PM
Security Audit — agent-trust-hub — project-analysis