gen-backend-handoff

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data that could contain malicious instructions designed to influence the agent's output or subsequent actions.
  • Ingestion points: The skill ingests data from git diff, git log, gh pr diff, and user-provided session context (SKILL.md).
  • Boundary markers: The skill uses a structured Markdown template for its output but does not employ specific delimiters or instruction-ignore blocks to isolate the ingested diff content.
  • Capability inventory: The skill executes repository inspection commands and writes files to the .handoffs/ directory (SKILL.md).
  • Sanitization: The instructions focus on excluding secrets but do not include sanitization or validation of code comments or commit messages that might contain embedded instructions.
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the gh CLI to fetch pull request information and diffs from GitHub, which is a well-known and trusted service.
  • [COMMAND_EXECUTION]: The skill executes various shell commands including git status, git log, and git diff to collect evidence for the handoff document. These commands are restricted to the local repository context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 02:05 PM
Security Audit — agent-trust-hub — gen-backend-handoff