plan-to-issues
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill synthesizes potentially untrusted data from conversation logs and repository files into development plans.
- Ingestion points: Reads from the current conversation and codebase understanding as primary inputs (SKILL.md).
- Boundary markers: The instructions lack explicit delimiters or specific directives to ignore malicious instructions that might be embedded in the source text.
- Capability inventory: The skill uses the 'gh' tool to create external issues and writes markdown files to the local file system.
- Sanitization: No content validation, escaping, or filtering is described for the data before it is published or saved.
Audit Metadata