ai-detector
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill acts on untrusted user-provided content to perform analysis and generate reports.
- Ingestion points: The skill ingests arbitrary text provided by users (described as 'user-provided content' in SKILL.md) to detect AI generation patterns.
- Boundary markers: Absent; the instructions do not specify using delimiters or ignore-instructions to isolate the analyzed content from the agent's logic.
- Capability inventory: The agent is instructed to generate an HTML report and include a 'download link for the analyzed content'. This involves rendering data into a specific format and potentially interacting with file-handling tools.
- Sanitization: No sanitization logic is described. If a user provides content containing malicious HTML or JavaScript, there is a risk the agent might reflect these payloads into the generated report, leading to cross-site scripting (XSS) or other content injection issues.
Audit Metadata