skills/vanilla-bar/kernel/self-review/Gen Agent Trust Hub

self-review

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests and processes data from external files and git diffs, which introduces a potential for indirect prompt injection.\n
  • Ingestion points: Content from files specified in $ARGUMENTS, git diff output, and project-specific review guidelines in .agents/review-perspectives.md (SKILL.md).\n
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when passing analyzed content to the sub-agent.\n
  • Capability inventory: The skill can read local files, execute git commands, and invoke a general-purpose sub-agent (SKILL.md).\n
  • Sanitization: No sanitization or validation is applied to the content before it is processed by the sub-agent.\n- [COMMAND_EXECUTION]: The skill executes a git diff command to retrieve changes for review. The command is static and used for its intended purpose within the development workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 12:35 PM
Security Audit — agent-trust-hub — self-review