sast-sqli
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of analyzing untrusted codebases.
- Ingestion points: The skill reads source code and architecture documentation (sast/architecture.md) from the environment.
- Boundary markers: The instructions do not implement specific boundary markers or 'ignore' commands when processing code snippets, which may allow malicious content within the code to influence the subagents' analysis logic.
- Capability inventory: The agent can write report files (sast/*.md) and initiate multiple subagents to process the data.
- Sanitization: There is no evidence of sanitization applied to the source code snippets before they are analyzed by the LLM.
Audit Metadata