piv-review-changes

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, specifically git status, git diff, and git ls-files, to programmatically determine the scope of code changes within the repository.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it reads and analyzes content from arbitrary files in the repository. Instructions embedded in analyzed code could potentially influence agent behavior during the review process.
  • Ingestion points: Processes file content retrieved via git diff and direct file reads for all new and modified files as specified in SKILL.md.
  • Boundary markers: There are no delimiters or instructions to ignore embedded commands within the analyzed code, which could lead to the agent inadvertently following instructions found in the data.
  • Capability inventory: The skill utilizes file system read access, execution of git commands, and the ability to write review reports to the .claude/code-reviews/ directory.
  • Sanitization: No escaping, filtering, or validation is performed on the ingested file content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 04:27 PM
Security Audit — agent-trust-hub — piv-review-changes