changelog

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The instructions employ repetitive, high-urgency language such as "MANDATORY IMPORTANT MUST ATTENTION" and "NO EXCEPTIONS" throughout the SKILL.md file to force specific agent behaviors and override standard decision-making processes regarding task complexity and workflow progression.\n- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing untrusted data from the repository (git diffs and source code) without sanitization or explicit delimiters. (1) Ingestion points: File contents and git diff output (2) Boundary markers: Absent (3) Capability inventory: Read, Write, Edit, Bash, Grep, Glob, Task, TaskCreate (4) Sanitization: Absent.\n- [COMMAND_EXECUTION]: The skill requires the execution of shell commands through the Bash tool, specifically git diff and git show, to extract the repository information necessary for generating documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 09:18 AM