draft-pull-request
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard
gitandgh(GitHub CLI) commands to retrieve repository context (branch names, logs, diffs) and perform the final PR creation. These operations are essential to the skill's primary functionality. - [INDIRECT_PROMPT_INJECTION]: The skill processes data that could be influenced by external actors:
- Ingestion points: Data enters the agent's context through
git logandgit diffoutput inSKILL.mdduring the context gathering phase. - Boundary markers: The instructions do not define specific delimiters to separate user/attacker-controlled code/commit content from the agent's internal instructions.
- Capability inventory: The skill has the capability to execute shell commands via
gh pr createinSKILL.md. - Sanitization: No explicit sanitization or filtering of the ingested diff/log content is performed before generating the PR body. While this represents a theoretical attack surface common to all code-summarization tools, the risk is low and inherent to the task.
Audit Metadata