peach-check
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
gh(GitHub CLI) tool to list workflow runs and fetch logs from theSonarSource/peachee-jsrepository. These commands are used for data retrieval related to the skill's primary purpose. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data (GitHub Action logs) and interpolates it into sub-agent instructions.
- Ingestion points: Job logs are fetched via the GitHub API and passed to sub-agents as the
LOG_CONTENTvariable inSKILL.md(Step 1.5). - Boundary markers: The skill uses
<job-logs>and</job-logs>tags to delimit the untrusted content. - Capability inventory: Sub-agents have access to read local documentation (
docs/peach-main-analysis.md) and the orchestrator has access to theghCLI tool. - Sanitization: No sanitization or escaping of the log content is performed before it is provided to the sub-agents.
Audit Metadata