zj-to-tickets
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources which could contain malicious instructions.
- Ingestion points: The agent is instructed to fetch and read the full body and comments of specs or issues from external URLs or local paths (SKILL.md).
- Boundary markers: No specific delimiters are used for the external content, but the skill implements a 'Quiz the user' loop requiring explicit approval before publishing.
- Capability inventory: The agent can write local files to the .scratch directory and perform network operations to publish issues to trackers like GitHub or Linear.
- Sanitization: No explicit sanitization or filtering of the ingested content is defined.
- [EXTERNAL_DOWNLOADS]: The skill fetches data from external issue trackers and specification URLs. These downloads are performed on well-known platforms (GitHub, Linear) for the purpose of gathering project context and do not involve executable payloads.
- [NO_CODE]: The skill is composed strictly of markdown-based instructions and metadata, containing no scripts, binaries, or other executable components.
Audit Metadata