frontend-code-review

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill analyzes untrusted external data (frontend source code), which creates a surface for indirect prompt injection. Malicious instructions embedded in the code could attempt to influence the agent's review or proposed fixes.\n
  • Ingestion points: Processes .tsx, .ts, and .js files as instructed in SKILL.md.\n
  • Boundary markers: The skill lacks specific delimiters or instructions to ignore embedded commands within the analyzed code.\n
  • Capability inventory: While the skill itself has no scripts, its instructions suggest that the agent can apply code fixes, which implies file-system write access on agent platforms.\n
  • Sanitization: No sanitization of the input code is performed.\n- [NO_CODE]: The skill consists entirely of Markdown instructions and metadata. There are no executable scripts or binaries included, which significantly reduces the risk of direct malicious code execution.\n- [EXTERNAL_DOWNLOADS]: The skill contains a documentation reference to a public GitHub issue (https://github.com/langgenius/dify/issues/29168). This is a reference to a well-known service and is used solely for developer context, posing no security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 06:27 PM
Security Audit — agent-trust-hub — frontend-code-review