sentry-security
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and search through user-provided code files, which constitutes an unvalidated input stream. Adversarial instructions hidden within the analyzed source code could potentially influence the agent's execution logic.
- Ingestion points: User-provided source code, diffs, and endpoints are ingested into the agent's context for analysis in SKILL.md.
- Boundary markers: The instructions lack explicit delimitation (e.g., XML tags or backticks with specific ignore-instructions) for the code content, making it difficult for the agent to distinguish between data and instructions.
- Capability inventory: The agent is granted access to the Read, Grep, Glob, and Bash tools, providing a significant capability surface if an injection attack succeeds.
- Sanitization: There are no directives to sanitize, escape, or validate the content of the files being reviewed before they are processed by the agent.
Audit Metadata