issues
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub issue titles, bodies, and comments, which could be used to host malicious instructions intended to manipulate the agent's behavior during the planning or implementation phase.
- Ingestion points: External issue data is ingested via
gh issue viewandgh issue listas specified inSKILL.mdandreferences/create.md. - Boundary markers: The instructions do not define clear delimiters or use "ignore embedded instructions" warnings when the agent processes the external issue content.
- Capability inventory: The skill has the capability to create git worktrees, modify the local filesystem, mutate GitHub objects via
gh issuecommands, and invoke other powerful execution skills such asfix-itandtest-it. - Sanitization: No explicit sanitization, filtering, or validation of the ingested issue content is described before it is integrated into the agent's operational context.
Audit Metadata