sast-graphql

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted source code from a target project to identify security flaws. This activity inherently creates a surface for indirect prompt injection, where malicious content in the analyzed codebase could attempt to influence the logic or output of the subagents used by the skill.
  • Ingestion points: The skill reads code files from the user's project and the sast/architecture.md file to provide context for subagents (SKILL.md).
  • Capability inventory: The skill has the ability to read project files, write analysis reports to the sast/ directory, and launch subagents to perform parallel analysis.
  • Boundary markers: The prompts provided to the subagents do not explicitly include delimiters or instructions to ignore potential commands embedded within the code snippets being analyzed.
  • Sanitization: There is no explicit mention of sanitizing or escaping the content of the analyzed files before including them in the subagent prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 03:34 AM
Security Audit — agent-trust-hub — sast-graphql