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
ghCLI 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, andgit diffto collect evidence for the handoff document. These commands are restricted to the local repository context.
Audit Metadata