author-byline
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to audit rendered HTML and HTTP responses from potentially untrusted external websites to verify SEO metadata and bylines. This creates an attack surface where a malicious website could embed instructions designed to manipulate the agent's logic or extract information.
- Ingestion points: Rendered HTML content and HTTP response headers retrieved from external URLs as specified in
SKILL.md. - Boundary markers: The instructions do not define clear delimiters or specific warnings to ignore embedded natural language instructions within the data being audited.
- Capability inventory: The skill enables the agent to read, process, and report on the structure and content of external web pages, which could lead to secondary actions if the agent interprets data as commands.
- Sanitization: There is no evidence of content sanitization or filtering to remove potential injection vectors from the ingested HTML or header data.
Audit Metadata