to-spec
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest conversation context and repository data, which are potentially untrusted sources, and use them to generate content for an external issue tracker.\n
- Ingestion points: Conversation history and codebase content (SKILL.md).\n
- Boundary markers: The skill provides a clear Markdown template for the output, which helps structure the generated content, though it lacks explicit instructions to disregard malicious prompts embedded within the source data.\n
- Capability inventory: The skill includes the capability to publish generated text to an external issue tracker (SKILL.md).\n
- Sanitization: There are no specific instructions provided for sanitizing or escaping the content derived from the conversation or codebase before publication.\n- [NO_CODE]: The skill does not include any executable scripts, binaries, or automated shell commands. It consists entirely of Markdown instructions for the AI model and a basic configuration file.
Audit Metadata