skills/rheinmir/setup/caveman-review/Gen Agent Trust Hub

caveman-review

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing external pull request data and incorporating summarized findings into local file paths and logs.
  • Ingestion points: Pull request diffs and source code files provided by the user (SKILL.md).
  • Boundary markers: Absent; the skill does not specify delimiters or guidelines to ignore instructions embedded within the processed code diffs.
  • Capability inventory: File system write access to create files in llmwiki/wiki/draft/cave/ and modify llmwiki/wiki/index.md and llmwiki/wiki/log.md (SKILL.md).
  • Sanitization: No explicit sanitization or validation of the summarized strings (the <ten> variable) is provided before use in file operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 09:06 AM
Security Audit — agent-trust-hub — caveman-review