snap-plan
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it fetches and processes content from external GitHub issues which are under the control of potentially untrusted users.
- Ingestion points: The command
gh issue view <number>inSKILL.mdimports external issue data into the agent's active context. - Boundary markers: Absent. The instructions do not specify any delimiters or safety warnings to ignore instructions embedded within the fetched issue content.
- Capability inventory: The agent uses
gh issue view(read), performs codebase exploration (read), and usesgh issue comment(write). An attacker could potentially influence how the agent explores the code or what it posts in the final comment. - Sanitization: Absent. There are no steps to sanitize or validate the issue content before the agent uses it to generate the implementation plan.
Audit Metadata