higress-daily-report
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- PROMPT_INJECTION (LOW): Detected a surface for Indirect Prompt Injection. The skill processes untrusted external content that could potentially contain malicious instructions meant to manipulate the agent's behavior.
- Ingestion points: The skill retrieves issue titles, bodies, and user comments from the
alibaba/higressrepository usinggh searchandgh issue viewcommands (identified inSKILL.md). - Boundary markers: Absent. The instructions do not define delimiters or specific warnings to ignore instructions embedded within the retrieved GitHub content.
- Capability inventory: The agent is authorized to perform state-changing actions on GitHub, including
gh issue comment,gh issue close, andgh issue edit, and sends summarized data to a Discord channel (identified inSKILL.md). - Sanitization: Absent. No evidence of input validation, escaping, or filtering of the fetched GitHub data is provided before it is used for 'intelligent analysis' or report generation.
- COMMAND_EXECUTION (SAFE): The skill utilizes the standard GitHub CLI (
gh) for repository interactions. All command patterns observed use static parameters or structured data requests, with no evidence of shell injection or arbitrary command execution vulnerabilities.
Audit Metadata