dryrunsecurity/remediation

Helps fix security vulnerabilities identified by DryRunSecurity. Activates when the user shares a DryRunSecurity comment (from a GitHub PR or GitLab MR) or asks for help fixing any security finding including SQL injection, XSS, CSRF, SSRF, path traversal, command injection, authentication bypass, authorization flaws, and prompt injection. Researches authoritative sources and applies fixes grounded in the user's specific codebase context.

Quality

99%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

DryRunSecurity Finding Format

Name: dryrunsecurity/remediation
Rating: 0.99 (1 reviews)
Author: dryrunsecurity

DryRunSecurity findings follow this format:

<summary paragraph describing what the PR/MR introduces>

<details>
<summary>
[emoji] Vulnerability Title in <code>path/to/file.ext</code>
</summary>

| **Vulnerability** | Vulnerability Name |
|:---|:---|
| **Description** | Detailed explanation... |

<Permalink to affected lines>
</details>

Key Elements to Extract

Element	Location	Example
Vulnerability type	Table row	"Prompt Injection", "Cross-Site Scripting"
File path	`<code>` tag in summary	`openhands/runtime/file_ops.py`
Line numbers	Permalink	`#L231-L232` → lines 231-232
Description	Table row	Attack scenario and why it's vulnerable
Severity	Emoji	`:yellow_circle:` = needs attention, none = blocking

Example Parsing

Summary: "Prompt Injection in <code>openhands/.../file_ops.py</code>"
→ Vulnerability: Prompt Injection
→ File: openhands/runtime/plugins/agent_skills/file_ops/file_ops.py
→ Lines: 231-232 (from permalink)
→ Issue: User input concatenated directly into LLM prompt without sanitization

Install with Tessl CLI

npx tessl i dryrunsecurity/remediation

VULNERABILITY_TYPES.md