to-tickets
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from external sources which could contain malicious instructions.
- Ingestion points: The skill is designed to fetch and read the full body and comments of issues from URLs or read local specification files provided by the user (SKILL.md).
- Boundary markers: There are no defined delimiters or instructions to the agent to disregard instructions found within the fetched external text.
- Capability inventory: The skill allows the agent to explore the codebase, write files to the local filesystem (under the .scratch/ directory), and perform network operations to interact with issue tracker APIs like GitHub or Linear (SKILL.md).
- Sanitization: No sanitization or validation of the external content is performed before it is integrated into the agent's context.
Audit Metadata