NYC

review-post-task

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill creates an attack surface where untrusted data from the repository can influence agent behavior.
  • Ingestion points: Untrusted content enters the context via git diff commands in SKILL.md (Steps 1.1 and 2.1).
  • Boundary markers: Absent. The agent receives raw diff data without explicit delimiters or instructions to ignore embedded natural language commands within the code.
  • Capability inventory: The skill authorizes the agent to 'Fix each issue directly' (Step 1.3), granting it file-write and modification privileges based on its interpretation of the (potentially malicious) input.
  • Sanitization: Absent. There is no mechanism to filter or sanitize instructions embedded in code comments or strings before the agent processes them.
  • Command Execution (LOW): The skill executes local shell commands to interact with the version control system.
  • Evidence: Usage of git diff --stat, git diff, and git add -p in SKILL.md. While these are standard tools, they are the mechanism through which untrusted data is pulled into the agent's reasoning loop.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 12:48 PM