brida-reflex-change-review-risk
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches live availability data and documentation from the author's own infrastructure (llms.txt, agent.md, agent.json).
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: Ingests untrusted code change summaries and environment state from the project repository (SKILL.md).
- Boundary markers: Explicit delimiters for the incoming change summary data are not specified in the instructions.
- Capability inventory: Classifies review risk levels and implements matching logic via MCP, SDK, or REST interfaces (SKILL.md).
- Sanitization: Mitigates risk by requiring that parsing, policy enforcement, and authorization remain in deterministic host code rather than LLM prompts (SKILL.md).
Audit Metadata