> For clean Markdown of this page, append .md to its URL. For the complete documentation index, see https://www.superagent.sh/llms.txt.


Check whether a coding agent follows its own policy when it reads repository content.

# Untrusted repository content in coding agents


[← Back to attack scenarios](https://www.superagent.sh/docs/products/red-teaming/attack-scenarios)

Coding agents use repository content to understand a project. This scenario checks whether material from the repository can influence a coding agent beyond the user's instructions or the agent's permitted scope.

Use it when an agent reads code or project files supplied by different contributors. Findings identify the trust boundary between repository content and the agent's behavior.

The app lists this scenario as **Compromise a coding agent through repository content** (`AG-14`) in [Agent Red Teaming](https://www.superagent.sh/docs/products/red-teaming/agents).

## Standards and guidance

[OWASP Agentic Top 10 (2026), ASI01 Agent Goal Hijack](https://genai.owasp.org/resource/owasp-top-10-for-agentic-applications-for-2026/)

---
Source: https://www.superagent.sh/docs/products/red-teaming/attack-scenarios/coding-agent-repository-content
Index: https://www.superagent.sh/llms.txt
