github-issue-creator
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data such as error logs and voice notes which may contain malicious instructions designed to subvert the agent's behavior.
- Ingestion points: User-provided bug reports and logs are ingested and transformed via the SKILL.md logic.
- Boundary markers: The skill utilizes a structured Markdown template but lacks explicit instructions to ignore instructions embedded within the source logs.
- Capability inventory: The skill's primary capability is writing Markdown draft files to the project's issues directory.
- Sanitization: The skill contains specific guidelines to replace sensitive data like project names and user IDs with placeholders.
Audit Metadata