migrate-issues
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill processes external content from GitHub issues and comments, creating an attack surface where untrusted data could potentially contain instructions aimed at influencing the agent's behavior.
- Ingestion points: Data is ingested from external source repositories via issue bodies and comments as described in SKILL.md.
- Boundary markers: The skill specifies markdown delimiters (horizontal rules) and headers for content separation, but does not provide an explicit command to the agent to ignore embedded instructions within the source data.
- Capability inventory: The agent is authorized to write to GitHub by creating new issues and comments in a target repository.
- Sanitization: The skill includes mandatory formatting requirements, such as wrapping mentions in backticks and expanding issue references to full URLs, which helps prevent unintended user notifications and incorrect cross-repository linking.
Audit Metadata