xy-xhs-headline
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user-supplied data, such as topics, industries, and existing content, to generate headlines.
- Ingestion points: The skill takes user input in the form of topics, industry descriptions, and old headlines as defined in the 'Step 1' workflow in
SKILL.md. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the user-provided strings.
- Capability inventory: The skill lacks dangerous capabilities such as file system writes, network requests, or system command execution.
- Sanitization: The instructions involve extracting core elements from user input but do not specify escaping or validation techniques to mitigate injection risks.
- [SAFE]: No suspicious patterns related to credential theft, obfuscated URLs, remote code execution, or unauthorized privilege escalation were identified. The referenced internal skill names (e.g.,
xy-opener,xy-content-scan) are consistent with the author's namespace and represent standard internal routing.
Audit Metadata