ywh-triage
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is comprised solely of markdown instructions and a reference document. It does not include any executable scripts, shell commands, or tool invocations that could pose a risk to the host environment.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data in the form of bug bounty report drafts and program scope documents.
- Ingestion points: SKILL.md requires two primary inputs: the draft report and the program scope.
- Boundary markers: None explicitly defined in the instructions to separate system instructions from user data.
- Capability inventory: The skill performs text analysis only. No subprocesses, network operations, or file system writes are requested or used.
- Sanitization: No specific sanitization or filtering of input text is implemented.
- Risk Assessment: Given the complete lack of dangerous capabilities (sinks), the risk of indirect prompt injection leading to system compromise or unauthorized actions is negligible. Malicious instructions within a report would only be able to influence the AI's triage verdict for that specific report.
Audit Metadata