scanning-for-xss-vulnerabilities

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it instructs the agent to ingest and analyze untrusted external data (source code) without implementing security boundaries.
  • Ingestion points: The skill uses the Read and Grep tools to retrieve and analyze user-provided code files.
  • Boundary markers: There are no instructions to wrap untrusted content in delimiters or specific warnings for the agent to ignore instructions embedded within the code being scanned.
  • Capability inventory: The agent has access to WebFetch (network), Read (filesystem), and Grep (filesystem), which provides a high-impact surface for an attacker if an injection succeeds.
  • Sanitization: No validation or sanitization of the input code is performed before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 08:27 AM
Security Audit — agent-trust-hub — scanning-for-xss-vulnerabilities