code-review-recent-changes

Pass

Audited by Gen Agent Trust Hub on Jul 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes several shell commands to gather context for the review, including git diff, git log, git rev-parse, and gh issue view. These are used to compare branches or commits and fetch issue specifications from the local environment and GitHub.
  • [PROMPT_INJECTION]: As the skill ingests and processes untrusted data from git logs, diffs, and external issue trackers, it has a surface for indirect prompt injection. A malicious actor could potentially embed instructions in commit messages or issue comments to influence the agent's review verdict. * Ingestion points: Commit logs, code diffs, and issue descriptions or comments. * Boundary markers: No explicit delimiters are used in the prompt templates when passing this data to sub-agents. * Capability inventory: File system access, shell command execution (git/gh), and sub-agent spawning. * Sanitization: No explicit sanitization or filtering of the ingested content is performed before interpolation into the sub-agent briefs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 19, 2026, 03:47 PM
Security Audit — agent-trust-hub — code-review-recent-changes