hreng-burnout
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect prompt injection vulnerability surface detected due to ingestion of untrusted data.\n
- Ingestion points: Analyzes git log data, Jira ticket descriptions, and PagerDuty incident notes as described in
SKILL.md.\n - Boundary markers: The instructions do not implement delimiters or specific safety instructions to distinguish ingested data from core agent instructions.\n
- Capability inventory: Uses shell execution for git logs and depends on tool-based data retrieval for external metrics.\n
- Sanitization: The provided validation script
scripts/validate-hreng-burnout.pyensures structural integrity of reports but does not sanitize or filter the content of ingested data for malicious prompts.
Audit Metadata