Skills
Navigate
skills/francostino/opencode-skills-collection/frontend-security-coder/Gen Agent Trust Hub

frontend-security-coder

Warn

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: MEDIUMINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
  • [METADATA_POISONING]: The frontmatter in SKILL.md contains deceptive metadata, specifically a future date_added field set to '2026-02-27' and a risk level of 'critical' that is inconsistent with the skill's instructions, potentially misleading users or security scanners.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions in SKILL.md describe processing and rendering user-generated content and rich text, which establishes a vulnerability surface for indirect prompt injection.
  • Ingestion points: Instructions in SKILL.md identify user-supplied inputs and rich text editor data as primary ingestion points for untrusted data.
  • Boundary markers: The skill includes instructions to 'Maintain separation between trusted and untrusted content' and provides guidelines for context-aware encoding.
  • Capability inventory: No scripts were provided for analysis; however, SKILL.md outlines capabilities for dynamic DOM manipulation and browser security configuration (CSP).
  • Sanitization: The instructions explicitly mandate the use of DOMPurify and allowlist-based validation for all dynamic content to mitigate injection risks.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 27, 2026, 01:29 PM