market-copy

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability to indirect prompt injection by ingesting untrusted data from external URLs.
  • Ingestion points: The skill uses WebFetch to retrieve and parse content from user-provided URLs in SKILL.md under Phase 1.
  • Boundary markers: There are no specified delimiters (e.g., XML tags or triple backticks) or explicit instructions to the agent to disregard instructions found within the fetched content.
  • Capability inventory: The skill possesses network read capabilities (WebFetch) and file-writing capabilities (creating COPY-SUGGESTIONS.md).
  • Sanitization: There is no evidence of content validation or filtering of the HTML/text retrieved from target pages before it is processed by the analysis frameworks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:07 PM
Security Audit — agent-trust-hub — market-copy