bug-triage-prep
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's functionality is restricted to triaging bug reports within the One Horizon ecosystem. No evidence of malicious intent, hidden commands, or unauthorized network activity was found. The tools referenced (list-bugs, get-task-details) are legitimate components of the vendor's MCP infrastructure.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external, untrusted content from bug reports.
- Ingestion points: Untrusted data enters the context through the
list-bugsandget-task-detailstool calls specified in the workflow of SKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded commands within the bug reports are provided in the skill's logic.
- Capability inventory: The skill is limited to data retrieval and enrichment for reporting; it lacks high-risk capabilities such as file system writes, shell execution, or arbitrary network requests.
- Sanitization: There are no instructions to sanitize or validate the bug content before it is processed into the final triage output.
Audit Metadata