ai-prompt-injection
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a documentation guide for penetration testers and bug bounty hunters to understand and test for AI-related vulnerabilities. It does not perform network operations, file system modifications, or execution of scripts.
- [PROMPT_INJECTION]: The skill contains example strings commonly used in prompt injection attacks, such as "Ignore previous instructions" and "print your system prompt". These are present as literal examples within the documentation to illustrate testing methods and are not used as instructions for the agent to override its own safety protocols.
- [INDIRECT_PROMPT_INJECTION]: The skill describes the concept of indirect prompt injection and provides an example of hidden instructions inside an HTML comment. This content is purely educational and identifies a vulnerability surface for testers rather than introducing a vulnerability into the skill's execution environment.
- [NO_CODE]: The skill consists entirely of markdown documentation. It does not include any Python or Node.js scripts, nor does it request access to sensitive tools or external dependencies.
Audit Metadata