website-to-signals

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from external websites.
  • Ingestion points: The website_url parameter in SKILL.md instructions.
  • Boundary markers: Absent; there are no instructions to the agent to ignore or delimit potentially malicious text within the fetched website content.
  • Capability inventory: Limited to standard web browsing and text output; no advanced capabilities like file writing or subprocess execution are requested.
  • Sanitization: Absent; the skill does not specify any filtering or validation of the retrieved content.
  • [NO_CODE]: The skill package contains no executable scripts or code files, relying solely on instructional markdown.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 07:31 PM
Security Audit — agent-trust-hub — website-to-signals