webpage-to-markdown

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection attacks because it ingests and processes content from external, untrusted webpages.
  • Ingestion points: Content is fetched from a public URL provided by the user in the 'Workflow' section of SKILL.md.
  • Boundary markers: Absent. The skill does not instruct the agent to use delimiters or ignore instructions found within the fetched content.
  • Capability inventory: The skill utilizes webpage-reading tools and provides the ability to write output to a user-specified file path.
  • Sanitization: Absent. There is no mention of filtering or sanitizing the extracted text to neutralize potential malicious instructions before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 04:05 AM
Security Audit — agent-trust-hub — webpage-to-markdown