agentsight-code-review

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to retrieve project history and code changes for the review process.
  • Evidence: Step 1 in SKILL.md executes git diff origin/main..HEAD, git diff --stat origin/main..HEAD, and git log --oneline origin/main..HEAD.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from source code changes. Malicious instructions hidden in code comments or files could influence the agent's logic during the review.
  • Ingestion points: The output of the git diff command is directly processed by the agent in SKILL.md.
  • Boundary markers: None; the skill lacks specific instructions to ignore or delimit embedded commands within the diff content.
  • Capability inventory: The skill has access to shell execution via git commands.
  • Sanitization: No sanitization or verification is applied to the code content before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:58 AM