to-issues
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from repository files that may contain malicious instructions designed to manipulate the agent's behavior during issue creation or backlog management.
- Ingestion points: The skill reads from
issues/*.md,issues/BACKLOG.md,issues/ARCHIVE.md,CONTEXT.md, anddocs/REQUIREMENTS-AND-NOTES.md. - Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' directives for content extracted from these files.
- Capability inventory: The agent possesses file system read and write capabilities within the repository to manage the issue tracker.
- Sanitization: Absent. The skill does not perform validation or sanitization on the external markdown content before incorporating it into the workflow.
Audit Metadata