skills/utkusen/sast-skills/sast-jwt/Gen Agent Trust Hub

sast-jwt

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an inherent attack surface because it is designed to ingest and analyze untrusted source code. While malicious instructions embedded in a target codebase could theoretically attempt to influence the agent's reasoning, this functionality is necessary for the skill's primary purpose as a security scanner.
  • Ingestion points: Reads the codebase and architecture documents.
  • Boundary markers: Not explicitly defined in the analysis instructions.
  • Capability inventory: Limited to reading files and writing results to the local directory.
  • Sanitization: No specific sanitization of analyzed code is implemented before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 03:34 AM
Security Audit — agent-trust-hub — sast-jwt